Sentence Embeddings using Definition Sentences
نویسندگان
چکیده
自然言語文をベクトルとして表現する文埋め込みは,深層学習を用いた自然言語処理の基礎技術として盛んに研究されており,特に自然言語推論 (Natural Language Inference; NLI) タスクに基づく文埋め込み手法が成功を収めている.しかし,これらの手法は大規模な NLI データセットを必要とすることから,そのような データが整備された言語以外については高品質な文埋め込みの構築が期待できないという問題がある.本研究ではこの問題を解決するため,NLI データと比べて多くの言語において整備が行われている言語資源である辞書に着目し,辞書の定義文を用いた文埋め込み手法を提案する.また,標準的なベンチマークを用いた評価実験を通し,提案手法は既存の タスクに基づく文埋め込み手法と同等の性能を実現すること,評価タスクの性質や評価データの抽出方法により性能に差異が見られること,これら2手法を統合することでより高い性能を実現できることを示す.
منابع مشابه
Suggesting Sentences for ESL using Kernel Embeddings
Sentence retrieval is an important NLP application for English as a Second Language (ESL) learners. ESL learners are familiar with web search engines, but generic web search results may not be adequate for composing documents in a specific domain. However, if we build our own search system specialized to a domain, it may be subject to the data sparseness problem. Recently proposed word2vec part...
متن کاملEmbedRank: Unsupervised Keyphrase Extraction using Sentence Embeddings
Keyphrase extraction is the task of automatically selecting a small set of phrases that best describe a given free text document. Supervised keyphrase extraction requires large amounts of labeled training data and generalizes very poorly outside the domain of the training data. At the same time, unsupervised systems have poor accuracy, and often do not generalize well, as they require the input...
متن کاملUnsupervised Text Summarization Using Sentence Embeddings
Dense vector representations of words, and more recently, sentences, have been shown to improve performance in a number of NLP tasks. We propose a method to perform unsupervised extractive and abstractive text summarization using sentence embeddings. We compare multiple variants of our systems on two datasets, show substantially improved performance over a simple baseline, and performance appro...
متن کاملTowards Generalizable Sentence Embeddings
In this work, we evaluate different sentence encoders with emphasis on examining their embedding spaces. Specifically, we hypothesize that a “high-quality” embedding aids in generalization, promoting transfer learning as well as zero-shot and one-shot learning. To investigate this, we modify Skipthought vectors to learn a more generalizable space by exploiting a small amount of supervision. The...
متن کاملEvaluating Compositionality in Sentence Embeddings
An important frontier in the quest for human-like AI is compositional semantics: how do we design systems that understand an infinite number of expressions built from a finite vocabulary? Recent research has attempted to solve this problem by using deep neural networks to learn vector space embeddings of sentences, which then serve as input to supervised learning problems like paraphrase detect...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Shizen gengo shori
سال: 2023
ISSN: ['1340-7619', '2185-8314']
DOI: https://doi.org/10.5715/jnlp.30.125