paper-with-me

Papers

MIPA: Mutual Information Based Paraphrase Acquisition via Bilingual Pivoting

2017-11-01 · IJCNLP 2017 11 · Tomoyuki Kajiwara, Mamoru Komachi, Daichi Mochihashi

We present a pointwise mutual information (PMI)-based approach to formalize paraphrasability and propose a variant of PMI, called MIPA, for the paraphrase acquisition. Our paraphrase acquisition method first acquires lexical paraphrase pairs by bilingual pivoting and then reranks them by PMI and distributional similarity. The complementary nature of information from bilingual corpora and from monolingual corpora makes the proposed method robust. Experimental results show that the proposed method substantially outperforms bilingual pivoting and distributional similarity themselves in terms of metrics such as MRR, MAP, coverage, and Spearman{'}s correlation.

📄 PDF Abstract BibTeX

Code (1)

tmu-nlp/pmi-ppdb 공식 구현

Tasks

Learning Word EmbeddingsSemantic Textual SimilarityWord AlignmentWord Embeddings

Similar Papers 제목 키워드 기반

A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models

2026-08-15 · Amrit Gopinath, Raghul, Durairaj Thenmozhi arxiv

We investigate whether Mixture-of-Experts (MoE) language models develop linguistically structured expert routing during bilingual language acquisition. Inspired by the Declarative-Procedural framework, we analyze lexical…

Language Acquisition

Paraphrase Acquisition from Image Captions

2023-01-26 · Marcel Gohsen, Matthias Hagen, Martin Potthast, Benno Stein

We propose to use image captions from the Web as a previously underutilized resource for paraphrases (i.e., texts with the same "message") and to create and analyze a corresponding dataset. When an image is reused on the…

ArticlesImage Captioning

Paraphrasing Revisited with Neural Machine Translation

2017-04-01 · EACL 2017 4 · Jonathan Mallinson, Rico Sennrich, Mirella Lapata

Recognizing and generating paraphrases is an important component in many natural language processing applications. A well-established technique for automatically extracting paraphrases leverages bilingual corpora to find…

Machine TranslationQuestion AnsweringSemantic ParsingSemantic Role Labeling+1

Optimizing rgb-d semantic segmentation through multi-modal interaction and pooling attention

2023-11-19 · Shuai Zhang, Minghong Xie

Semantic segmentation of RGB-D images involves understanding the appearance and spatial relationships of objects within a scene, which requires careful consideration of various factors. However, in indoor environments, t…

DecoderSegmentationSemantic Segmentation

Power-Law Distributions for Paraphrases Extracted from Bilingual Corpora

2012-04-01 · EACL 2012 4 · Spyros Martzoukos, Christof Monz
Machine Translation