A | B | C | E | F | G | H | I | J | K | L | M | N | O | P | R | S | T | U | V | W | X | Y | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | 392/435 abstracts have nonzero citations | ||||||||||||||||||||||
2 | 35 abstracts wth >= 100 citations | ||||||||||||||||||||||
3 | Title | S2 Link | Task | Baseline (Neural/Non) | Norm Task | Expert Domain | Non-narrative domain | Language | Unconventional adaptation setting | Norm Coarse Method (new) | Norm Fine Method (new) | Norm Coarse Method (ext) | Norm Fine Method (ext) | Norm Coarse Method (appl) | Norm Fine Method (appl) | Norm Coarse Method (baselines) | Norm Fine Method (baselines) | #Citations | |||||
4 | Research on Task Discovery for Transfer Learning in Deep Neural Networks | https://semanticscholar.org/paper/196ac6d19ba025fd450f2ba6c657a96907818fe7 | NER, Dependency Parsing | Neural | NER, SP | Biomedical | Label variation | DC, MC | PT, LA | 2 | 28.4025974 | ||||||||||||
5 | Reversing Gradients in Adversarial Domain Adaptation for Question Deduplication and Textual Entailment Tasks | https://semanticscholar.org/paper/38a9765ca11f3141b944df482a8d882bd277141f | Question deduplication, RTE | Neural | TC, NLI | Finance | Forum | Label variation | MC | LA | 4 | 16 | |||||||||||
6 | UHH-LT at SemEval-2019 Task 6: Supervised vs. Unsupervised Transfer Learning for Offensive Language Detection | https://semanticscholar.org/paper/498f2e0ac488c3ccc96b32584cba3dd93223bc54 | Offensive language detection | Neural | TC | Label variation | DC, MC | LA, PT | 4 | ||||||||||||||
7 | Transferring User Interests Across Websites with Unstructured Text for Cold-Start Recommendation | https://semanticscholar.org/paper/d9669a0aeb9bd118dc03bdf94f1333a11e34c49d | Cold-start recommendation | Non-neural | MF | Label variation | MC | PI | SOTA | 4 | |||||||||||||
8 | NSIT@NLP4IF-2019: Propaganda Detection from News Articles using Transfer Learning | https://semanticscholar.org/paper/62c3cdea92e4b2a5414fcbd2c9a3dc4173e5dab3 | Propaganda Detection | Both | TC | Label variation | DC | PT | 4 | ||||||||||||||
11 | On the Evaluation of Contextual Embeddings for Zero-Shot Cross-Lingual Transfer Learning | https://semanticscholar.org/paper/d1eb4dfe24dd4009f6cb53bc089e3f43ee4678e2 | -- | Label variation, Unsupervised | 5 | ||||||||||||||||||
13 | Convolutional Neural Networks for Financial Text Regression | https://semanticscholar.org/paper/8d4d1f67f81cb8e12e0206f35ff13429e686b610 | Financial volatility forecasting | Neural | TRG | Finance | Label variation, Unsupervised | DC+MC | FP+PT | 6 | |||||||||||||
15 | Metric Learning for Graph-Based Domain Adaptation | https://semanticscholar.org/paper/eb42a03c93ff82187c80743a30f4eaec7c1c30ae | Sentiment Analysis | Non-neural | TC | Multi-Source | DC | PL | MC | FP | 6 | ||||||||||||
16 | Transfer Learning Based Free-Form Speech Command Classification for Low-Resource Languages | https://semanticscholar.org/paper/9ad68df478b6571ca9dd70deddeb0fb80f7b0850 | SLU (Spoken Language Understanding) | Both | SLU | Conv | Multi-Source | MC | FP | 7 | |||||||||||||
17 | A Joint Named-Entity Recognizer for Heterogeneous Tag-setsUsing a Tag Hierarchy | https://semanticscholar.org/paper/95b42a217b6e02808e52c707db7087fa217b530c | NER | Neural | NER | Clinical | Multi-Source | DC | PL | MC | EN, LA | 7 | |||||||||||
18 | An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels | https://semanticscholar.org/paper/3186deef8c2aa3839b40c7f56b05807592cbe918 | Large-scale Multi-label Text Classification (LMTC) | Neural | TC | Clinical | Multi-Source | DC | PT | 7 | |||||||||||||
20 | Semi-supervised Stochastic Multi-Domain Learning using Variational Inference | https://semanticscholar.org/paper/5b60e5216b66cfc7f9e0c41de154915efe6e5ef3 | Sentiment Analysis, Language Identification | Neural | TC | Multi-Source | MC | FP | MC | LA | 7 | ||||||||||||
21 | An Interpretable Neural Network with Topical Information for Relevant Emotion Ranking | https://semanticscholar.org/paper/b55d773030b5a16d7580aa063bd0f3032babe4af | Relevant emotion ranking | Neural | TRN | Multi-Source | MC | PI | SOTA | 7 | |||||||||||||
22 | Convolutional Neural Network for Universal Sentence Embeddings | https://semanticscholar.org/paper/d82732de6336dd6443ff33cccbb92ced0196ecc1 | NLI-style NLU tasks | Neural | NLI | Multi-Source, Label variation | DC | PT | DC | PT | 7 | ||||||||||||
23 | Estimating the influence of auxiliary tasks for multi-task learning of sequence tagging tasks | https://semanticscholar.org/paper/aa95b13370d663ff805fcba1b4493aae07166ef3 | -- | Online | 7 | ||||||||||||||||||
25 | Towards Open Domain Event Trigger Identification using Adversarial Domain Adaptation | https://semanticscholar.org/paper/97d3c0a402097a8c03ed66bd0e73ac4d4ac70b31 | Event Extraction | Neural | NER | Literature | Online | MC | LA | MC | FP | 8 | |||||||||||
26 | Improving Citation Polarity Classification with Product Reviews | https://semanticscholar.org/paper/1011dc13c78e7e805ae93470ccf9053ea247772b | Citation polarity classification | Neural | TC | Science | Online | MC, HY | AE, FP, IW, EN | 8 | |||||||||||||
30 | Transfer and Multi-Task Learning for Noun-Noun Compound Interpretation | https://semanticscholar.org/paper/03166b7ef32a7fac19b9562713dd870081da374f | Noun-noun compound interpretation (looks like a word pair relation classification task) | Neural | TC | Scheme difference | MC | LA, PI | 9 | ||||||||||||||
31 | Pushing the Limits of AMR Parsing with Self-Learning | https://semanticscholar.org/paper/31fad264bb767909e337c56aded6b45873d555ce | AMR parsing | Neural | SP | Scheme difference, Unsupervised | DC | PL | 10 | ||||||||||||||
32 | Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering | https://semanticscholar.org/paper/72a5158dae67ff034eaf3c345338cde32450b8fb | Multiple-choice QA | Neural | TC | Symmetric | MC | FP+LA | SOTA, DC | PT | 10 | ||||||||||||
36 | Adaptive Multi-Task Transfer Learning for Chinese Word Segmentation in Medical Text | https://semanticscholar.org/paper/576f800788ea0599b5490443e46a462bf86a0e2a | Chinese Word Segmentation | Neural | POS | Clinical | Forum | Unsupervised | MC | LA | MC | FP, PI, LA | 11 | ||||||||||
37 | Domain Adaptation for Syntactic and Semantic Dependency Parsing Using Deep Belief Networks | https://semanticscholar.org/paper/b5e026cad0edafc75b607c4b2d782cafcf692ed4 | Syntactic and semantic dependency parsing | Non-neural | SP | Unsupervised | MC | AE | DC+MC | PL+FP | 11 | ||||||||||||
39 | Sentence-Level Propaganda Detection in News Articles with Transfer Learning and BERT-BiLSTM-Capsule Model | https://semanticscholar.org/paper/7a6a26fd7a42393cf2865a43b91dacb04fe084ac | Propaganda Detection | Neural | TC | Conv | Unsupervised | MC | PI | 12 | |||||||||||||
40 | psyML at SemEval-2018 Task 1: Transfer Learning for Sentiment and Emotion Analysis | https://semanticscholar.org/paper/cbb50e3b4f5ac42e418ff1609d3b541b9b3e1e0a | Affect classification from Tweets | Neural | TC | Unsupervised | MC | PI | 12 | ||||||||||||||
42 | Semi-supervised Domain Adaptation for Dependency Parsing | https://semanticscholar.org/paper/1bdd14d6cfceb033edcf84ce471a99abfd780754 | Dependency parsing | Neural | SP | Unsupervised | DC, MC, HY | LA, FP, DS, PT | 12 | ||||||||||||||
45 | Transformer Based Multi-Source Domain Adaptation | https://semanticscholar.org/paper/e505303ba5287f468773fbef22ab1abf6875efca | -- | Unsupervised | 12 | ||||||||||||||||||
46 | Transfer Learning for Entity Recognition of Novel Classes | https://semanticscholar.org/paper/2e500cf63b0a61ef346aa3f2e34ef65f67f0d703 | Entity extraction [REPRODUCTION/SURVEY PAPER] | Both | NER | Clinical, DefSec | Conv, Twitter | Unsupervised | MC | FP, PI | 13 | ||||||||||||
47 | Improving Event Coreference Resolution by Learning Argument Compatibility from Unlabeled Data | https://semanticscholar.org/paper/1a08438003d7a58b3982eb3cbc8198ff84e77eba | Event Argument Compatibility, Event Coreference | Neural | NLI | Unsupervised | DC+MC | PI+PL | 13 | ||||||||||||||
48 | Model Adaptation for Personalized Opinion Analysis | https://semanticscholar.org/paper/6acc451af7a70e615ca3fd548716166a67210af2 | Sentiment analysis | Non-neural | TC | Unsupervised | MC | PI | DC, MC | IL, PI+LA | 13 | ||||||||||||
50 | The Necessity of Combining Adaptation Methods | https://semanticscholar.org/paper/d9442344241cf86171cc277def3c67ff7064af7a | -- | Unsupervised | 13 | ||||||||||||||||||
51 | Biber Redux: Reconsidering Dimensions of Variation in American English | https://semanticscholar.org/paper/76405eca8f0cfdbbf4748b3a8481840d2890bdc1 | -- | Unsupervised | 13 | ||||||||||||||||||
52 | Two Methods for Domain Adaptation of Bilingual Tasks: Delightfully Simple and Broadly Applicable | https://semanticscholar.org/paper/2b932e2a56e5b1c34c2a926c3a30cbcec84232a8 | Cross-lingual sentiment classification, Medical bilingual lexicon induction | Neural | TC, LI | Clinical | Conv, Twitter | Unsupervised | DC+MC, MC | PT+FP, LA | 15 | ||||||||||||
53 | XL-NBT: A Cross-lingual Neural Belief Tracking Framework | https://semanticscholar.org/paper/ff065acdde4b8b6cb1e0386924d72cdcee058503 | Dialog state tracking | Neural | TC | Conv | Unsupervised | MC | LA | MC | FP | 16 | |||||||||||
54 | Importance weighting and unsupervised domain adaptation of POS taggers: a negative result | https://semanticscholar.org/paper/5a08ee6a162462792d2e970381cd9fcdc641a8f2 | POS tagging | Non-neural | POS | Email, Forum | Unsupervised | HY | IW | HY | IW | 16 | |||||||||||
57 | LIMSI-COT at SemEval-2017 Task 12: Neural Architecture for Temporal Information Extraction from Clinical Narratives | https://semanticscholar.org/paper/af9659c6b7c0225567329387590259444acc3900 | Event extraction, Attribute extraction, Temporal relation classification | Both | TC, NER | Clinical | Unsupervised | DC, MC, HY | FR, NO, DS | 16 | |||||||||||||
58 | Cross-lingual Transfer Learning for Japanese Named Entity Recognition | https://semanticscholar.org/paper/f20e9840951aa1d93951a184e5aa30f5f641d975 | NER | Neural | NER | Unsupervised | MC | PI, FP | 16 | ||||||||||||||
59 | Robust Domain Adaptation for Relation Extraction via Clustering Consistency | https://semanticscholar.org/paper/e6c946147945f82bbed614ca61582b76698d88e1 | Relation extraction | Non-neural | TC | Unsupervised | DC+MC | PL+EN | DC, MC | FP, LA, PL | 16 | ||||||||||||
61 | Single and Cross-domain Polarity Classification using String Kernels | https://semanticscholar.org/paper/8f5b2c4794ab5caba0f3903f0adf376cfe931c46 | Polarity classification/Sentiment analysis | Non-neural | TC | Unsupervised | MC | FP | MC | FP | 16 | ||||||||||||
63 | Active Sentiment Domain Adaptation | https://semanticscholar.org/paper/9759c425008506dac507ed26057febd9cab822b8 | Sentiment analysis | Non-neural | TC | Unsupervised multi-source | DC+MC | AL+LA | DC, MC | FP, AL | 16 | ||||||||||||
64 | Online Updating of Word Representations for Part-of-Speech Tagging | https://semanticscholar.org/paper/e101bd3a90524d4011eddc0ab8fdc2d3b4bea8ca | POS tagging | Non-neural | POS | Email, Forum | Unsupervised multi-source | MC | FR | 17 | |||||||||||||
65 | UofL at SemEval-2016 Task 4: Multi Domain word2vec for Twitter Sentiment Classification | https://semanticscholar.org/paper/ea685afa91cdeecde26cd6c9ca1d42e6768e4204 | Sentiment analysis | Neural | TC | Unsupervised multi-source | DC | PT | 19 | ||||||||||||||
66 | Domain Adaptation for Authorship Attribution: Improved Structural Correspondence Learning | https://semanticscholar.org/paper/25312b9dfaff44ee6c41aaf3e3f3e4cf6677efc7 | Authorship attribution | Non-neural | TC | MC | FP | MC | FP | 19 | |||||||||||||
67 | Modeling Social Norms Evolution for Personalized Sentiment Classification | https://semanticscholar.org/paper/e1fa9206eb753b1a7424777f951c84ddd30d35a5 | Sentiment analysis | Non-neural | TC | MC | LA+PI | DC, MC | IL, PI, LA | 20 | |||||||||||||
69 | Improving SCL Model for Sentiment-Transfer Learning | https://semanticscholar.org/paper/9a8e5715935c1e688152e9cd82b2bb966b786f24 | Sentiment analysis | Non-neural | TC | MC+HY | FP+IW | MC | FP | 20 | |||||||||||||
71 | Sentiment Relevance | https://semanticscholar.org/paper/e8fe08c7965921c1f0b9f17921f4a0e996f36401 | Sentiment Relevance | Non-neural | TC | DC+MC+HY | FP+PL+DS | 22 | |||||||||||||||
72 | Named Entity Recognition without Labelled Data: A Weak Supervision Approach | https://semanticscholar.org/paper/bedb476a4a691e27169563f2fd275c2f44efd187 | NER | Neural | NER | Finance | DC | PL | DC, MC | AE, PT | 23 | ||||||||||||
73 | A Multi-Domain Web-Based Algorithm for POS Tagging of Unknown Words | https://semanticscholar.org/paper/fbcad87da202f9330bd31be782cacd55d9813a97 | POS tagging | Non-neural | POS | Biomedical | DC | PL | 23 | ||||||||||||||
75 | Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting | https://semanticscholar.org/paper/f2f3c83db919a2429c4fcad2d0a0ed4e5294354a | NLI-style NLU tasks | Neural | NLI | MC | LA | DC | PT | 24 | |||||||||||||
76 | Closing the Gap: Domain Adaptation from Explicit to Implicit Discourse Relations | https://semanticscholar.org/paper/7b8d7847251fa73e78e0cad9ef78e25490345539 | Discourse relation identification, framed as binary classification for each relation type | Neural | NLI | MC+HY | AE+IW | 25 | |||||||||||||||
77 | Exploring and Predicting Transferability across NLP Tasks | https://semanticscholar.org/paper/d1206ccabd1980848f14472d6548251c2fab7963 | -- | 25 | |||||||||||||||||||
79 | Investigating Transferability in Pretrained Language Models | https://semanticscholar.org/paper/cb5c8050532856cc8fecb210e0fdcfcd6b14de69 | -- | Neural | 26 | ||||||||||||||||||
80 | Filling the Gap: Semi-Supervised Learning for Opinion Detection Across Domains | https://semanticscholar.org/paper/be103f7cd975ea13e98e10ea419666923c89b665 | Opinion detection | Non-neural | TC | DC+HY | PL+IW | 26 | |||||||||||||||
81 | Predicting proficiency levels in learner writings by transferring a linguistic complexity model from expert-written coursebooks | https://semanticscholar.org/paper/48b8b0b0f0023220e993a5ecee6b928ec2a67fbb | Proficiency level prediction | Non-neural | TC | DC, MC, HY | FP, IW, DS, NO | 29 | |||||||||||||||
82 | Multilingual Semantic Parsing And Code-Switching | https://semanticscholar.org/paper/1536e32fd1f56307720db2f0fd3a045cd3bff0f7 | Semantic Parsing | Neural | SP | Conv | DC, MC | PT, LA, PL | 30 | ||||||||||||||
83 | On Robustness and Domain Adaptation using SVD for Word Sense Disambiguation | https://semanticscholar.org/paper/82ea0ff74d598b60fad4e9a6737280651870c2b5 | WSD | Non-neural | WSD | MC | FP | 30 | |||||||||||||||
84 | Combining Natural and Artificial Examples to Improve Implicit Discourse Relation Identification | https://semanticscholar.org/paper/2c6fae1eb35e2a64399631651a4a9adf733d68e6 | Discourse relation identification | Non-neural | NLI | MC, HY | DS, PI, EN, FP | 30 | |||||||||||||||
86 | Label-aware Double Transfer Learning for Cross-Specialty Medical Named Entity Recognition | https://semanticscholar.org/paper/552dc303366045f3e510f9ee51d88a0531fd6614 | NER | Neural | NER | Clinical | MC | LA | MC, HY | FP, LA, IW | 31 | ||||||||||||
87 | This paper proposes | https://semanticscholar.org/paper/250c2ee0e0f405f0e0b246f88a74779220cd0ef7 | WSD | Non-neural | WSD | MC | FP | 33 | |||||||||||||||
88 | Unsupervised Multi-Domain Adaptation with Feature Embeddings | https://www.aclweb.org/anthology/N15-1069.pdf | POS tagging | Non-neural | POS | Literature | Email, Forum | MC | FP | MC, SOTA | FP, AE, NO | 46 | |||||||||||
89 | Neural Adaptation Layers for Cross-domain Named Entity Recognition | https://semanticscholar.org/paper/4c934343f95950fe10894c35961783b72dc7a8e0 | NER | Neural | NER | MC | PA+FP | MC | PI, LA | 49 | |||||||||||||
90 | Exploiting Feature Hierarchy for Transfer Learning in Named Entity Recognition | https://semanticscholar.org/paper/622e05f5d3dd430644288d5048f6050f37947de7 | NER | Non-neural | NER | Biomedical | MC | FP | MC | PI | 51 | ||||||||||||
91 | ETS: Domain Adaptation and Stacking for Short Answer Scoring | https://semanticscholar.org/paper/469ce82c2ca0f91c34cd7f600d2c1ac51d23e587 | Scoring short text answers | Non-neural | TRG | Science | MC | FP | 52 | ||||||||||||||
92 | Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling | https://semanticscholar.org/paper/06a1bf4a7333bbc78dbd7470666b33bd9e26882b | -- | 55 | |||||||||||||||||||
93 | Domain Adaptation with Adversarial Training and Graph Embeddings | https://semanticscholar.org/paper/561ede166947a8bedb8be9acff182913156e06c6 | Tweet classification | Neural | TC | MC | LA | DC | PL | 61 | |||||||||||||
94 | Frustratingly Easy Neural Domain Adaptation | https://semanticscholar.org/paper/644ff0a9596bfa72c2f9328ec24d8726121a2b63 | Slot tagging in dialogues | Neural | NER | Conv | MC | FP | MC | FP | 62 | ||||||||||||
95 | Recall-Oriented Learning of Named Entities in Arabic Wikipedia | https://semanticscholar.org/paper/fb6b1221f553369a1e3a47830af6ec7753a37f40 | NER | Non-neural | NER | DC+MC | LA+PL | 64 | |||||||||||||||
96 | Word Segmentation of Informal Arabic with Domain Adaptation | https://semanticscholar.org/paper/3adf1a0fbdc7458388e8cbe6ab10889806a17dca | Arabic word segmentation | Non-neural | POS | Forum | MC | FP | 67 | ||||||||||||||
97 | Transfer Capsule Network for Aspect Level Sentiment Classification | https://semanticscholar.org/paper/c1abff438508a80524b525b2e4b6bd4a5c40b101 | Aspect-level sentiment analysis | Neural | TC | MC | LA | MC, SOTA | LA | 70 | |||||||||||||
98 | Cross-Genre and Cross-Domain Detection of Semantic Uncertainty | https://semanticscholar.org/paper/eecb2d79b4e600b735b58787d65d45253673c46c | Semantic uncertainty cue recognition | Non-neural | NER | Biomedical | MC | FP | 70 | ||||||||||||||
99 | Aspect-augmented Adversarial Networks for Domain Adaptation | https://semanticscholar.org/paper/4668d812461a4878a0ca61ee8d5564d5b4a025de | Text classification | Neural | TC | Clinical | MC | FP+LA | MC | AE | 73 | ||||||||||||
101 | Estimating Class Priors in Domain Adaptation for Word Sense Disambiguation | https://semanticscholar.org/paper/796f991064b5cb119df30945f77f1f46cf9c401b | WSD | Non-neural | WSD | MC | PI | 74 | |||||||||||||||
103 | Zero-Shot Transfer Learning for Event Extraction | https://semanticscholar.org/paper/5a3abc60f0c91a255b1a86843d9e97ab7d63bf08 | Event Extraction | Neural | TRN | MC | FP | 79 | |||||||||||||||
107 | Training Conditional Random Fields Using Incomplete Annotations | https://semanticscholar.org/paper/e9aeeb7b8363f0d0094b94fcc8cfe26382e05d2a | Japanese word segmentation, POS tagging | Non-neural | POS | Clinical | Conv | MC | LA | 82 | |||||||||||||
108 | Semi-supervised Speech Act Recognition in Emails and Forums | https://semanticscholar.org/paper/fb58fa1992f3e4e331386af7ed253ca7ce030c86 | Speech Act Recognition | Non-neural | TC | Conv, Email, Forum | DC+HY | IW+PL | 82 | ||||||||||||||
109 | Lessons from Natural Language Inference in the Clinical Domain | https://semanticscholar.org/paper/f2588de5173fb047192dbb93d62ce6636bdf46bd | NLI | Both | NLI | Clinical | DC, MC | PT, FP | 91 | ||||||||||||||
113 | Cross-Lingual Transfer Learning for POS Tagging without Cross-Lingual Resources | https://semanticscholar.org/paper/e8bef413503471559d66146b651afc9c513b5b37 | POS tagging | Neural | POS | MC | LA | 97 | |||||||||||||||
116 | Domain Adaptation meets Active Learning | https://semanticscholar.org/paper/06935a5c7b5a592e960f7bbac739750d8ebdcf01 | Sentiment analysis | Non-neural | TC | DC+MC | AL+LA | DC, MC | FP, AL | 99 | |||||||||||||
118 | Embedding Semantic Similarity in Tree Kernels for Domain Adaptation of Relation Extraction | https://semanticscholar.org/paper/9666727600e633617984cbf431ea1495277bd970 | Relation extraction | Non-neural | TC | MC | FP | HY | IW | 114 | |||||||||||||
119 | Efficient Graph-Based Semi-Supervised Learning of Structured Tagging Models | https://semanticscholar.org/paper/53fd142f3c52ac68cedcfcdea3b0d350a6a75db6 | POS tagging | Non-neural | POS | Biomedical | DC | PL | DC | PL | 116 | ||||||||||||
120 | Semi-Supervised QA with Generative Domain-Adaptive Nets | https://semanticscholar.org/paper/807e421679d4a9d629d2fad1f60f28787dca60e7 | Reading comprehension | Neural | RC | DC+MC | LA+PL+FP | MC | LA | 116 | |||||||||||||
121 | Domain Adaptation with Active Learning for Word Sense Disambiguation | https://semanticscholar.org/paper/689b4bec1cf9dbfd6af293eff2aeefd8c18085b2 | WSD | Non-neural | WSD | DC+MC+HY | AL+IW+PI | 124 | |||||||||||||||
122 | Domain Adaptation of Rule-Based Annotators for Named-Entity Recognition Tasks | https://semanticscholar.org/paper/1cf53c62906a48b9d607f94468bf777855199a28 | NER | Non-neural | NER | MC | HE | SOTA | 125 | ||||||||||||||
123 | MITRE at SemEval-2016 Task 6: Transfer Learning for Stance Detection | https://semanticscholar.org/paper/c522d992fa71ce163bf90db9ca1861e0805f2b5b | Stance detection | Neural | TC | DC | PT | 129 | |||||||||||||||
126 | Automatic Domain Adaptation for Parsing | https://semanticscholar.org/paper/9a222218041f07dd63d0e8c34b0402a88d50c463 | Syntactic parsing | Non-neural | SP | Biomedical, Literature | Conv | MC | EN | DC, MC | PL, EN | 159 | |||||||||||
127 | Cross-Domain Co-Extraction of Sentiment and Topic Lexicons | https://semanticscholar.org/paper/ae4b9a4c818c78e5d132af230cd23875f0ee5314 | Sentiment and Topic lexicon extraction | Non-neural | TC | DC+MC+HY | LA+PL+IW | DC, MC+HY | LA+IW, PL | 166 | |||||||||||||
128 | Hierarchical Bayesian Domain Adaptation | https://semanticscholar.org/paper/5f126695342ea2bab2aa6eb971563f5d91d00aa0 | NER, Dependency parsing | Non-neural | NER, SP | MC | FP | MC | FP | 189 | |||||||||||||
129 | How Transferable are Neural Networks in NLP Applications? | https://semanticscholar.org/paper/f21b36a5cfba94bbc6ed5c3642e1e46057deccaf | -- | 239 | |||||||||||||||||||
132 | Event Detection and Domain Adaptation with Convolutional Neural Networks | https://semanticscholar.org/paper/765797a79be0c0b26cd0ebe51b894a3555106dfa | Event extraction | Neural | NER | MC | FP | 248 | |||||||||||||||
134 | Cross-Language Text Classification Using Structural Correspondence Learning | https://semanticscholar.org/paper/fb3054bcaf1b6de06979cc50ea51d3f5e3560a19 | Sentiment analysis | Non-neural | TC | MC | FP | MC | FP | 261 | |||||||||||||
136 | What to do about bad language on the internet | https://semanticscholar.org/paper/c928e453122fa7c0658e02a7aa07a623d4e5b679 | -- | 325 | |||||||||||||||||||
137 | Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval | https://semanticscholar.org/paper/c3b8367a80181e28c95630b9b63060d895de08ff | Query classification, Web search | Neural | TC, TRN | MC | LA | SOTA | 332 | ||||||||||||||
138 | Universal Sentence Encoder for English | https://semanticscholar.org/paper/101fc5b569ee9b9e11850f8b5d86a6dd74ee7258 | Text classification, NLI | Neural | TC, NLI | Forum | DC+MC | PT+LA | SOTA, DC | PT | 348 | ||||||||||||
139 | Deep multi-task learning with low level tasks supervised at lower layers | https://semanticscholar.org/paper/03ad06583c9721855ccd82c3d969a01360218d86 | Syntactic chunking, CCG supertagging, POS-tagging | Neural | POS | MC | LA | 354 | |||||||||||||||
140 | Multi-Task Deep Neural Networks for Natural Language Understanding | https://semanticscholar.org/paper/658721bc13b0fa97366d38c05a96bf0a9f4bb0ac | NLI-style NLU tasks | Neural | NLI | Science | MC | LA | DC | PT | 585 | ||||||||||||
141 | Instance Weighting for Domain Adaptation in NLP | https://semanticscholar.org/paper/b672ef69f60aea81220d658963445c41e60bb0e3 | POS tagging, Entity type classification, Spam filtering | Non-neural | POS, TC | Biomedical | HY | IW | 784 | ||||||||||||||
142 | Supervised Learning of Universal Sentence Representations from Natural Language Inference Data | https://semanticscholar.org/paper/ee7b883e35d754ae4f71c21bb71f9f03e4ffbb2c | Text classification (Sentiment, Question, Subjectivity, Opinion Polarity), Semantic relatedness (NLI, Paraphrase detection, STS), Caption-Image retrieval | Neural | TC, NLI | DC | PT | DC, MC | FP, PT | 1340 | |||||||||||||
143 | Domain Adaptation with Structural Correspondence Learning | https://semanticscholar.org/paper/9fa8d73e572c3ca824a04a5f551b602a17831bc5 | POS tagging | Non-neural | POS | Biomedical | MC | FP | 1431 |