Semantic Search as Extractive Paraphrase Span Detection
In this paper, we approach the problem of semantic search by framing the search task as paraphrase span detection, i.e. given a segment of text as a query phrase, the task is to identify its paraphrase in a given document, the same modelling setup as typically used in extractive question answering. On the Turku Paraphrase Corpus of 100,000 manually extracted Finnish paraphrase pairs including their original document context, we find that our paraphrase span detection model outperforms two strong retrieval baselines (lexical similarity and BERT sentence embeddings) by 31.9pp and 22.4pp respectively in terms of exact match, and by 22.3pp and 12.9pp in terms of token-level F-score. This demonstrates a strong advantage of modelling the task in terms of span retrieval, rather than sentence similarity. Additionally, we introduce a method for creating artificial paraphrase data through back-translation, suitable for languages where manually annotated paraphrase resources for training the span detection model are not available.
Code (0)
등록된 구현이 없습니다.
Tasks
Extractive Question-AnsweringQuestion AnsweringRetrievalSentenceSentence EmbeddingsSentence SimilarityTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Semantic Search as Extractive Paraphrase Span Detection
In this paper, we approach the problem of semantic search by framing the search task as paraphrase span detection, i.e. given a segment of text as a query phrase, the task is to identify its paraphrase in a given documen…
Extractive Question-AnsweringQuestion AnsweringRetrievalSentence+3Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Text
AI-generated text detection has attracted increasing attention as powerful language models approach human-level generation. Limited work is devoted to detecting (partially) AI-paraphrased texts. However, AI paraphrasing …
DiversityText DetectionExploring Multitask Learning for Low-Resource AbstractiveSummarization
This paper explores the effect of using multitask learning for abstractive summarization in the context of small training corpora. In particular, we incorporate four different tasks (extractive summarization, language mo…
Abstractive Text SummarizationExtractive SummarizationLanguage ModelingLanguage ModellingExploring Multitask Learning for Low-Resource Abstractive Summarization
This paper explores the effect of using multitask learning for abstractive summarization in the context of small training corpora. In particular, we incorporate four different tasks (extractive summarization, language mo…
Abstractive Text SummarizationExtractive SummarizationLanguage ModelingLanguage ModellingComposing Answer from Multi-spans for Reading Comprehension
This paper presents a novel method to generate answers for non-extraction machine reading comprehension (MRC) tasks whose answers cannot be simply extracted as one span from the given passages. Using a pointer network-st…
DecoderMachine Reading ComprehensionReading Comprehension