COLING

10,131 papers5,426 directions
The International Conference on Computational Linguistics serves as a venue for research at the intersection of linguistics, computer science, and artificial intelligence. Within the machine learning community, it provides a platform for the dissemination of work concerning natural language processing, semantic analysis, and discourse relation recognition. The venue documents both theoretical developments in computational linguistics and the application of statistical models to language data. A notable portion of the research published at this venue focuses on speech processing and recognition, with a specific emphasis on Mandarin and Taiwanese languages. Technical methodologies represented in its corpus include hybrid deep neural network architectures, denoising auto-encoders for speech enhancement, and neural network modeling for spoken document retrieval. The venue also incorporates proceedings from specialized meetings, such as the Conference on Computational Linguistics and Speech Processing (ROCLING). Prolific contributors to this venue include researchers such as Berlin Chen, Hsin-Min Wang, and Kuan-Yu Chen. Their research often explores the integration of machine learning with signal processing, including the development of real-time monitoring devices for phonation and software-based interfaces for speech systems. This reflects the venue's role in bridging linguistic theory with applied neural network techniques and speech technology.

Papers by Year

2026 2
2025 1,162
2024 2,178
2022 906
2020 1,209
2019 3
2018 539
2017 8
2016 415
2015 2
2014 259
2013 1
2012 401
2010 353
2008 198
2006 10
2004 202
2002 197
2000 177
1998 152
1996 214
1994 215
1992 217
1990 203
1988 171
1986 156
1984 52
1982 144
1980 94
1973 65
1969 172
1967 38
1965 24

Top Research Directions

Research directions most represented by papers from this venue.

Mitigating Data Scarcity in Low Resource Language Processing 320
Overcoming the Coverage Limitations of Formal Grammars 200
Contextual Disambiguation of Polysemous Words 147
Processing Text with Implicit Word Boundaries 145
Automating Lexical Semantic Resource Construction 133
The Language Bias of English Centric Benchmarks 126
Modeling Syntactic Structure in Free Word Order Languages 122
Adapting Natural Language Processing to Dialectal Diversity 104
Processing Non-Compositional Semantics in Natural Language 102
The Empirical Validation Gap in Systems Research 102
The Performance Advantage of Localized Language Pretraining 101
The Expressive Limitations of Context-Free Grammars 93
Measuring Inter-Annotator Agreement for Reliable Data Curation 91
Pre-Training Language Models on Specialized Corpora 90
Factual Inaccuracy and Hallucination in Large Language Models 86

Top Authors

AuthorPapers
Min Zhang48
Xuanjing Huang40
Yue Zhang34
Deyi Xiong31
Ting Liu31
Qun Liu27
Timothy Baldwin26
Qiaoming Zhu25
Qi Zhang25
Wanxiang Che25
Chengqing Zong24
Hinrich Schuetze24
Bing Qin23
Kang Liu22
Maosong Sun22
Iryna Gurevych21
Rada Mihalcea20
Taro Watanabe20
Kentaro Inui19
hai zhao18

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Discriminative Induction of Sub-Tree Alignment using Limited Labeled Data2010
Discriminative Training for Near-Synonym Substitution2010
DL Meet FL: A Bidirectional Mapping between Ontologies and Linguistic Knowledge2010
Document Expansion Based on WordNet for Robust IR2010
Dual-Space Re-ranking Model for Document Retrieval2010
Dynamic Parameters for Cross Document Coreference2010
Effective Constituent Projection across Languages2010
Efficient Statement Identification for Automatic Market Forecasting2010
E-HowNet and Automatic Construction of a Lexical Ontology2010
EM-based Hybrid Model for Bilingual Terminology Extraction from Comparable Corpora2010
EMDC: A Semi-supervised Approach for Word Alignment2010
EMMA: A novel Evaluation Metric for Morphological Analysis2010
Emotion Cause Detection with Linguistic Constructions2010
End-to-End Coreference Resolution via Hypergraph Partitioning2010
Enhanced Sentiment Learning Using Twitter Hashtags and Smileys2010
Enhancing Cross Document Coreference of Web Documents with Context Similarity and Very Large Scale Text Categorization2010
Enhancing Morphological Alignment for Translating Highly Inflected Languages2010
Enhancing Multi-lingual Information Extraction via Cross-Media Inference and Fusion2010
Enriching Dictionaries with Images from the Internet - Targeting Wikipedia and a Japanese Semantic Lexicon: Lexeed -2010
Entity Disambiguation for Knowledge Base Population2010
Entity-Focused Sentence Simplification for Relation Extraction2010
Entity Linking Leveraging Automatically Generated Annotation2010
Estimating Linear Models for Compositional Distributional Semantics2010
Evaluating Dependency Representations for Event Extraction2010
Evaluating FrameNet-style semantic parsing: the role of coverage gaps in FrameNet2010
Evaluating N-gram based Evaluation Metrics for Automatic Keyphrase Extraction2010
Evaluating performance of grammatical error detection to maximize learning effect2010
Evaluation of Dependency Parsers on Unbounded Dependencies2010
Exploiting Background Knowledge for Relation Extraction2010
Exploiting Paraphrases and Deferred Sense Commitment to Interpret Questions more Reliably2010
Exploiting Salient Patterns for Question Detection and Question Retrieval in Community-based Question Answering2010
Exploiting Structured Ontology to Organize Scattered Online Opinions2010
Explore the Structure of Social Tags by Subsumption Relations2010
Exploring the Data-Driven Prediction of Prepositions in English2010
Exploring the Use of Word Relation Features for Sentiment Classification2010
Exploring variation across biomedical subdomains2010
“Expresses-an-opinion-about”: using corpus statistics in an information extraction approach to opinion mining2010
Expressing OWL axioms by English sentences: dubious in theory, feasible in practice2010
Extracting and Ranking Product Features in Opinion Documents2010
Extraction of Multi-word Expressions from Small Parallel Corpora2010
FactRank: Random Walks on a Web of Facts2010
Fast and Accurate Arc Filtering for Dependency Parsing2010
Fast-Champollion: A Fast and Robust Sentence Alignment Algorithm2010
Fast, Greedy Model Minimization for Unsupervised Tagging2010
Feature-Rich Discriminative Phrase Rescoring for SMT2010
Filling Knowledge Gaps in Text for Machine Reading2010
Filtered Ranking for Bootstrapping in Event Extraction2010
Finding the Storyteller: Automatic Spoiler Tagging using Linguistic Cues2010
Finite-state Scriptural Translation2010
Fluency Constraints for Minimum Bayes-Risk Decoding of Statistical Machine Translation Lattices2010

« prev Page 145/203 next »