The proceedings contain 65 papers. The topics discussed include: unsupervised term extraction for highly technical domains;a hybrid approach to cross-lingual product review summarization;augmenting operations research...
ISBN:
(纸本)9781952148255
The proceedings contain 65 papers. The topics discussed include: unsupervised term extraction for highly technical domains;a hybrid approach to cross-lingual product review summarization;augmenting operations research with auto-formulation of optimization models from problem descriptions;knowledge distillation based contextual relevance matching for e-commerce product search;accelerating the discovery of semantic associations from medical literature: mining relations between diseases and symptoms;machine translation impact in e-commerce multilingual search;ask-and-verify: span candidate generation and verification for attribute value extraction;consultation checklists: standardizing the human evaluation of medical note generation;towards need-based spoken language understanding model updates: what have we learned?;and calibrating imbalanced classifiers with focal loss: an empirical study.
The proceedings contain 1268 papers. The topics discussed include: UniGen: universal domain generalization for sentiment classification via zero-shot dataset generation;Multi-News+: cost-efficient dataset cleansing vi...
ISBN:
(纸本)9798891761643
The proceedings contain 1268 papers. The topics discussed include: UniGen: universal domain generalization for sentiment classification via zero-shot dataset generation;Multi-News+: cost-efficient dataset cleansing via LLM-based data annotation;FIZZ: factual inconsistency detection by zoom-in summary and zoom-out document;table question answering for low-resourced Indic languages;LLM-based agent society investigation: collaboration and confrontation in Avalon gameplay;when LLMs meets acoustic landmarks: an efficient approach to integrate speech into large language models for depression detection;speaking in wavelet domain: a simple and efficient approach to speed up speech diffusion model;eyes don’t lie: subjective hate annotation and detection with gaze;and ThinkingFair and Slow: on the efficacy of structured prompts for debiasing language models.
The proceedings contain 312 papers. The topics discussed include: language understanding for text-based games using deep reinforcement learning;building a shared world: mapping distributional to model-theoretic semant...
ISBN:
(纸本)9781941643327
The proceedings contain 312 papers. The topics discussed include: language understanding for text-based games using deep reinforcement learning;building a shared world: mapping distributional to model-theoretic semantic spaces;syntax-based rewriting for simultaneous machine translation;open extraction of fine-grained political statements;semantic annotation for microblog topics using Wikipedia temporal information;re-evaluating automatic summarization with BLEU and 192 shades of ROUGE;cross lingual sentiment analysis using modified BRAE;joint prediction for entity/event-level sentiment analysis using probabilistic soft logic models;combining geometric, textual and visual features for predicting prepositions in image descriptions;non-lexical neural architecture for fine-grained POS tagging;a model of zero-shot learning of spoken language understanding;and birds of a feather linked together: a discriminative topic model using link-based priors.
The proceedings contain 224 papers. The topics discussed include: translation modeling with bidirectional recurrent neural networks;a neural network approach to selectional preference acquisition;learning image embedd...
ISBN:
(纸本)9781937284961
The proceedings contain 224 papers. The topics discussed include: translation modeling with bidirectional recurrent neural networks;a neural network approach to selectional preference acquisition;learning image embeddings using convolutional neural networks for improved multi-modal semantics;identifying argumentative discourse structures in persuasive essays;policy learning for domain selection in an extensible multi-domain spoken dialogue system;a constituent-based approach to argument labeling with joint inference in discourse parsing;strongly incremental repair detection;semi-supervised Chinese word segmentation using partial-label learning with conditional random fields;and accurate word segmentation and POS tagging for Japanese microblogs: corpus annotation and joint modeling with lexical normalization.
The proceedings contain 145 papers. The topics discussed include: improving LSA-based summarization with anaphora resolution;data-driven approaches for information structure identification;using semantic relations to ...
The proceedings contain 145 papers. The topics discussed include: improving LSA-based summarization with anaphora resolution;data-driven approaches for information structure identification;using semantic relations to refine coreference decisions;semantic similarity for detecting recognition errors in automatic speech transcripts;a discriminative matching approach to word alignment;tell me what you do and i'll tell you what you are: learning occupation-related activities for biographies;investigating unsupervised learning for text categorization bootstrapping;kernel-based approach for automatic evaluation of naturallanguage generation technologies: application to automatic summarization;training neural network language models on very large corpora;automatically learning cognitive status for multi-document summarization of newswire;and a comparative study on language model adaptation techniques using new evaluation metrics.
The proceedings contain 130 papers. The special focus in this conference is on empirical Method in naturallanguageprocessing (emnlp) and conference on Computational naturallanguage Learning (CoNLL). The topics disc...
The proceedings contain 130 papers. The special focus in this conference is on empirical Method in naturallanguageprocessing (emnlp) and conference on Computational naturallanguage Learning (CoNLL). The topics discussed include: modelling compression with discourse constraints;learning unsupervised SVM classifier for answer selection;improving word alignment with bridge languages;getting the structure right for word alignment;improving statistical machine translation;large margin synchronous generation;incremental text structuring with online hierarchical ranking;similarity and partitioning in incremental generation of plural descriptions;foreign inclusion detection to improve parsing performance;improving query spelling correction;compressing trigram language models with golomb coding;joint morphological and syntactic disambiguation;global learning of labelled dependency trees;covington variations;online learning for deterministic dependency parsing;incremental dependency parsing using online learning;constraint satisfaction approach to dependency parsing;a conditional entropy-based external cluster evaluation measure;probabilistic coordination disambiguation;probabilistic models of nonprojective dependency trees;structured prediction models via the matrix-tree theorem;modelling polysemy in adjective classes;and RBMT Systems to produce bilingual corpus for SMT.
The proceedings contain 681 papers. The topics discussed include: attending to future tokens for bidirectional sequence generation;transfer learning between related tasks using expected label proportions;knowledge enh...
ISBN:
(纸本)9781950737901
The proceedings contain 681 papers. The topics discussed include: attending to future tokens for bidirectional sequence generation;transfer learning between related tasks using expected label proportions;knowledge enhanced contextual word representations;how contextual are contextualized word representations? comparing the geometry of BERT, ELMo, and GPT-2 embeddings;correlations between word vector sets;game theory meets embeddings: a unified framework for word sense disambiguation;guided dialog policy learning: reward estimation for multi-domain task-oriented dialog;multi-hop selector network for multi-turn response selection in retrieval-based chatbots;building task-oriented visual dialog systems through alternative optimization between dialog policy and language generation;knowledge-enriched transformer for emotion detection in textual conversations;using customer service dialogues for satisfaction analysis with context-assisted multiple instance learning;leveraging dependency forest for neural medical relation extraction;and open relation extraction: relational knowledge transfer from supervised data to unsupervised data.
The proceedings contain 324 papers. The topics discussed include: monolingual phrase alignment on parse forests;fast(er) exact decoding and global training for transition-based dependency parsing via a minimal feature...
ISBN:
(纸本)9781945626838
The proceedings contain 324 papers. The topics discussed include: monolingual phrase alignment on parse forests;fast(er) exact decoding and global training for transition-based dependency parsing via a minimal feature set;quasi-second-order parsing for 1-endpoint-crossing, page number-2 graphs;position-aware attention and supervised data improve slot filling;heterogeneous supervision for relation extraction: a representation learning approach;integrating order information and event relation for script event prediction;entity linking for queries by searching Wikipedia sentences;train-O-matic: large-scale supervised wordsense disambiguation in multiple languages without manual training data;universal semantic parsing;and past, present, future: a computational investigation of the typology of tense in 1000 languages.
The proceedings contain 34 papers. The topics discussed include: text-translation alignment: three languages are better than two;mapping multilingual hierarchies using relaxation labeling;improved alignment models for...
The proceedings contain 34 papers. The topics discussed include: text-translation alignment: three languages are better than two;mapping multilingual hierarchies using relaxation labeling;improved alignment models for statistical machine translation;cross-language information retrieval for technical documents;boosting applied to tagging and pp attachment;applying extrasentential context to maximum entropy based tagging with a large semantic and syntactic tagset;determining the specificity of nouns from text;language independent named entity recognition combining morphological and contextual evidence;and hybrid disambiguation of prepositional phrase attachment and interpretation.
The proceedings contain 56 papers. The topics discussed include: max-margin parsing;active learning and the total cost of annotation;induction of greedy controllers for deterministic treebank parsers;unsupervised WSD ...
The proceedings contain 56 papers. The topics discussed include: max-margin parsing;active learning and the total cost of annotation;induction of greedy controllers for deterministic treebank parsers;unsupervised WSD based on automatically retrieved examples: the importance of bias;VERBOCEAN: mining the web for fine-grained semantic verb relations;scaling web-based acquisition of entailment relations;bilingual parsing with factored estimation: using English to parse Korean;mining very-non-parallel corpora: parallel sentence and lexicon extraction via bootstrapping and EM;comparing and combining generative and posterior probability models: some advances in sentence boundary detection in speech;and automatic paragraph identification: a study across languages and domains.
暂无评论