A Unified Model for Word Sense Representation and Disambiguation

Chen, Xinxiong; Liu, Zhiyuan; Sun, Maosong

doi:10.3115/v1/d14-1110

Cited by 218 publications

(191 citation statements)

References 23 publications

(19 reference statements)

Supporting

Mentioning

186

Contrasting

Unclassified

Order By: Relevance

“…Most past canonicalization models use precision, recall, and F1 score to evaluate on the Semeval dataset (Mihalcea et al 2004). The current state-of-the-art performance on Semeval is an F1 score of 75.8% (Chen et al 2014). Since our canonicalization setup is different from the Semeval benchmark (we have an open vocabulary and no annotated ground truth for evaluation), our canonicalization For example, the carriage is mapped to carriage.n.02: a vehicle with wheels drawn by one or more horses.…”

Section: Canonicalization Statisticsmentioning

confidence: 99%

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Krishna

Zhu

Groth³

et al. 2017

Int J Comput Vis

4,158

3,078

View full text Add to dashboard Cite

Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that involve not just recognizing, but reasoning about our visual world. However, models used to tackle the rich content in images for cognitive tasks are still being trained using the same datasets designed for perceptual tasks. To achieve success at cognitive tasks, models need to understand the interactions and relationships between objects in an image. When asked "What vehicle is the person riding?", computers will need to identify the objects in an image as well as the relationships riding(man, carriage) and pulling(horse, carriage) to answer correctly that "the person is riding a horse-drawn carriage." In this paper, we present the Visual Genome dataset to enable the modeling of such relationships. We collect dense annotations of objects, attributes, and relationships within each image to learn these models. Specifically, our dataset contains over 108K images where each image has an average of 35 objects, 26 attributes, and 21 pairwise relationships between objects. We canonicalize the objects, attributes, relationships, and noun phrases in region descriptions and questions answer pairs to WordNet synsets. Together, these annotations represent the densest

show abstract

Section: Canonicalization Statisticsmentioning

confidence: 99%

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Krishna

Zhu

Groth³

et al. 2017

Int J Comput Vis

4,158

3,078

View full text Add to dashboard Cite

show abstract

“…(2) We will evaluate the performance of our OIWE models in various NLP applications. (3) We will also investigate possible extensions of our OIWE models, including multiple-prototype models for word sense embeddings (Huang et al, 2012;Chen et al, 2014), semantic compositions for phrase embeddings (Zhao et al, 2015) and knowledge representation (Bordes et al, 2013;Lin et al, 2015).…”

Section: Discussionmentioning

confidence: 99%

Online Learning of Interpretable Word Embeddings

Luo¹,

Liu²,

Luan³

et al. 2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

Word embeddings encode semantic meanings of words into low-dimension word vectors. In most word embeddings, one cannot interpret the meanings of specific dimensions of those word vectors. Nonnegative matrix factorization (NMF) has been proposed to learn interpretable word embeddings via non-negative constraints. However, NMF methods suffer from scale and memory issue because they have to maintain a global matrix for learning. To alleviate this challenge, we propose online learning of interpretable word embeddings from streaming text data. Experiments show that our model consistently outperforms the state-of-the-art word embedding methods in both representation ability and interpretability. The source code of this paper can be obtained from http: //github.com/skTim/OIWE.

show abstract

“…Previously, other approaches were introduced to utilise embeddings for supervised (Zhong and Ng, 2010;Rothe and Schütze, 2015; Taghipour and Ng, 2015) and knowledge-based WSD (Chen et al, 2014).…”

Section: Related Workmentioning

confidence: 99%

Proceedings of the Third Workshop on Discourse in Machine Translation

2017

View full text Add to dashboard Cite

We hope that workshops such as this one will continue to stimulate work on Discourse and Machine Translation, in a wide range of discourse phenomena and MT architectures.We would like to thank all the authors who submitted papers to the workshop, as well as all the members of the Program Committee who reviewed the submissions and delivered thoughtful, informative reviews. AbstractWe describe the design, the setup, and the evaluation results of the DiscoMT 2017 shared task on cross-lingual pronoun prediction. The task asked participants to predict a target-language pronoun given a source-language pronoun in the context of a sentence. We further provided a lemmatized target-language human-authored translation of the source sentence, and automatic word alignments between the source sentence words and the targetlanguage lemmata. The aim of the task was to predict, for each target-language pronoun placeholder, the word that should replace it from a small, closed set of classes, using any type of information that can be extracted from the entire document.We offered four subtasks, each for a different language pair and translation direction: English-to-French, Englishto-German, German-to-English, and Spanish-to-English.Five teams participated in the shared task, making submissions for all language pairs. The evaluation results show that all participating teams outperformed two strong n-gram-based language model-based baseline systems by a sizable margin. IntroductionPronoun translation poses a problem for machine translation (MT) as pronoun systems do not map well across languages, e.g., due to differences in gender, number, case, formality, or humanness, as well as because of language-specific restrictions about where pronouns may be used. For example, when translating the English it into French an MT system needs to choose between il, elle, and cela, while translating the same pronoun into German would require a choice between er, sie, and es. This is hard as selecting the correct pronoun may need discourse analysis as well as linguistic and world knowledge. Null subjects in pro-drop languages pose additional challenges as they express person and number within the verb's morphology, rendering a subject pronoun or noun phrase redundant. Thus, translating from such languages requires generating a pronoun in the target language for which there is no pronoun in the source.Pronoun translation is known to be challenging not only for MT in general, but also for Statistical Machine Translation (SMT) in particular (Le Nagard and Koehn, 2010;Hardmeier and Federico, 2010; Novák, 2011;. Phrase-based SMT (Koehn et al., 2013) was state of the art until recently, but it is gradually being replaced by Neural Machine Translation, or NMT, (Cho et al., 2014; Sutskever et al., 2014; Bahdanau et al., 2015;Luong et al., 2015). 1 NMT yields generally higher-quality translation, but is harder to analyze, and thus little is known about how well it handles pronoun translation. Yet, it is clear that it has access to larger context compa...

show abstract

A Unified Model for Word Sense Representation and Disambiguation

Cited by 218 publications

References 23 publications

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Online Learning of Interpretable Word Embeddings

Proceedings of the Third Workshop on Discourse in Machine Translation

Contact Info

Product

Resources

About