Investigating Lexical Substitution Scoring for Subtitle Generation

This paper investigates an isolated setting of the lexical substitution task of replacing words with their synonyms. In particular, we examine this problem in the setting of subtitle generation and evaluate state of the art scoring methods that predict the validity of a given substitution. The paper evaluates two context independent models and two contextual models. The major findings suggest that distributional similarity provides a useful complementary estimate for the likelihood that two Wordnet synonyms are indeed substitutable, while proper modeling of contextual constraints is still a challenging task for future research.

• Publication year

  2006

• Venue

  Conference on Computational Natural Language Learning

• Publication date

  2006-06-08

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1596276.1596286
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• The Third PASCAL Recognizing Textual Entailment Challenge

  2007cited by this paper
• A Neural Network for Text Representation

  2005cited by this paper
• The PASCAL Recognising Textual Entailment Challenge

  2005cited by this paper
• A Probabilistic Classification Approach for Lexical Textual Entailment

  2005cited by this paper
• The Distributional Inclusion Hypotheses and Lexical Entailment

  2005cited by this paper
• NIST Special Publication

  2005cited by this paper
• Finding Predominant Word Senses in Untagged Text

  2004cited by this paper
• Automatic Sentence Simplification for Subtitling in Dutch and English

  2004cited by this paper
• Multimodal, Multilingual Resources in the Subtitling Process

  2004cited by this paper
• Semantic distance in WordNet: An experimental, application-oriented evaluation of five measures

  2004cited by this paper
• Automatic speech summarization applied to English broadcast news speech

  2002cited by this paper
• Summarization beyond sentence extraction: A probabilistic approach to sentence compression

  2002cited by this paper
• The decomposition of human-written summary sentences

  1999cited by this paper
• Overview of the Seventh Text REtrieval Conference

  1998cited by this paper
• Automatic Retrieval and Clustering of Similar Words

  1998cited by this paper
• Producing Intelligent Telegraphic Text Reduction to provide an Audio Scanning Service for the Blind

  1998cited by this paper
• Query expansion using lexical-semantic relations

  1994cited by this paper
• A Semantic Concordance

  1993influential reference
• The measurement of observer agreement for categorical data.

  1977cited by this paper
• Mathematical structures of language

  1968cited by this paper

• Ar-SLoTE: A Recognizing Textual Entailment Tool for Arabic Question/Answering Systems

  2019cites this paper
• Arabic Logic Textual Entailment with Feature Extraction and Combination

  2018cites this paper
• A Lightweight and Efficient Mechanism for Fixing the Synchronization of Misaligned Subtitle Documents

  2016cites this paper
• Using a generic neural model for lexical substitution (Utiliser un modèle neuronal générique pour la substitution lexicale) [in French]

  2014cites this paper
• Finding Meaning in Context Using Graph Algorithms in Mono- and Cross-lingual Settings

  2013cites this paper
• Cross-lingual Sentence Compression for Subtitles

  2012cites this paper
• Paraphrastic Sentence Compression with a Character-based Metric: Tightening without Deletion

  2011cites this paper
• Source-Language Entailment Modeling for Translating Unknown Terms

  2009cites this paper
• Machine Learning Approaches to Text Representation Using Unlabeled Data Machine Learning Approaches to Text Representation Using Unlabeled Data

  2007cites this paper
• Instance Based Lexical Entailment for Ontology Population

  2007cites this paper
• FBK-irst: Lexical Substitution Task Exploiting Domain and Syntagmatic Coherence

  2007cites this paper
• HIT: Web based Scoring Method for English Lexical Substitution

  2007cites this paper
• Machine Learning Approaches to Text Representation using Unlabeled Data. (Approches d'apprentissage automatiques pour le représentation de textes à travers l'utilisation de données non-étiquetées)

  2006cites this paper
• Machine Learning Approaches to Text Representation using

  2006cites this paper