Challenge: Existing benchmarks for phrase-similarity compare phrases alone (without context) and phrases with context (with or without context).
Approach: They propose to use a dataset of 28K noun phrases accompanied by their contextual Wikipedia pages to train machine phrase embeddings.
Outcome: The proposed dataset improves ranking-models’ accuracy and pushes span selection models near human accuracy, which is 95% Exact Match (EM) on semantic search given a query phrase and a passage.

Similar Papers

Learning High-Quality and General-Purpose Phrase Representations (2024.findings-eacl)

Copied to clipboard

Challenge: Pre-trained language models for phrasal embeddings are unnecessarily complex and require to be pre-tuned on a corpus with context sentences.
Approach: They propose a framework to learn phrase representations in a context-free fashion.
Outcome: The proposed framework generates superior phrase embeddings while requiring a smaller model size.
Towards Better Context-aware Lexical Semantics:Adjusting Contextualized Representations through Static Anchors (2020.emnlp-main)

Copied to clipboard

Challenge: Recent research has shown that contextualized models generate dynamic embeddings for words in context, but static embedds are often overlooked in this trend towards contextualized modeling.
Approach: They propose a method that learns a transformation through static anchors and requires only another pre-trained model.
Outcome: The proposed method improves a range of benchmark tasks that test contextual variations of meaning across different usages of a word and across different words as they are used in context.
A Corpus to Learn Refer-to-as Relations for Nominals (L18-1)

Copied to clipboard

Challenge: Existing work on how to learn refer-to-as relations from large unlabeled corpora lacks coreferential information.
Approach: They propose to use Wikipedia to generate coreferential neural embeddings for nominals . they use coreference resolution as a proxy to evaluate the neural embeds for noun phrases .
Outcome: The proposed dataset can be leveraged to construct representations for coreferential nominals from Wikipedia.
Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations (D19-1)

Copied to clipboard

Challenge: Contextualized word representations are effective in downstream tasks such as question answering, named entity recognition, and sentiment analysis.
Approach: They propose to integrate pre-trained contextualized word representations into a neural network that captures the whole sentence and the word representation in the sentence.
Outcome: The proposed approach outperforms the state-of-the-art approach that makes use of non-contextualized word embeddings on multiple benchmark WSD datasets.
Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration (2021.emnlp-main)

Copied to clipboard

Challenge: Phrase representations derived from pretrained language models often lack lexical similarity to determine semantic relatedness.
Approach: They propose a contrastive fine-tuning objective that enables BERT to produce more powerful phrase embeddings by fine- tuning a dataset of diverse phrasal paraphrases and a large-scale dataset of phrases in context.
Outcome: The proposed model outperforms baseline models across phrase-level similarity tasks while also showing increased lexical diversity between nearest neighbors in the vector space.
Putting Evaluation in Context: Contextual Embeddings Improve Machine Translation Evaluation (P19-1)

Copied to clipboard

Challenge: Existing evaluation metrics are limited and can be easily portable to new languages.
Approach: They propose a simple unsupervised metric and additional supervised metrics which rely on contextual word embeddings to encode the translation and reference sentences.
Outcome: The proposed model outperforms existing metrics on the WMT 2017 dataset and is more accurate than existing models.
CoSimLex: A Resource for Evaluating Graded Word Similarity in Context (2020.lrec-1)

Copied to clipboard

Challenge: Existing methods to evaluate word embeddings ignore context and treat words in isolation.
Approach: They propose to build a new word embeddings-based dataset that provides context-dependent similarity measures.
Outcome: The proposed dataset provides context-dependent similarity measures and covers a well-resourced language (English) but a number of less-resource languages.
Contextualized Word Representations for Reading Comprehension (N18-2)

Copied to clipboard

Challenge: Reading comprehension (RC) is a high-level task in natural language understanding that requires reading a document and answering questions about its content.
Approach: They propose to provide a standard neural network for reading a document and answering a question about its content.
Outcome: The proposed model improves on the competitive SQuAD dataset by providing rich contextualized word representations and allowing it to choose between context-dependent and context-independent representations.
Word Embedding and WordNet Based Metaphor Identification and Interpretation (P18-1)

Copied to clipboard

Challenge: Existing models cannot identify exact metaphorical words within a sentence . current models do not rely on hand-crafted knowledge for training .
Approach: They propose an unsupervised learning method that identifies and interprets metaphors at word-level without preprocessing.
Outcome: The proposed method outperforms baseline models in two translation systems for English to Chinese showing that it paraphrases metaphors into their literal counterparts.
SPADE: Evaluation Dataset for Monolingual Phrase Alignment (L18-1)

Copied to clipboard

Challenge: Existing studies on sentential paraphrase detection focus on finer grained paraphrases, i.e., phrasal paraphrase.
Approach: They propose to use the SPADE to evaluate syntactic phrase alignment in paraphrasal sentences.
Outcome: The proposed method is compared with humans and provides benchmarks to show its performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations