paper-with-me

홈 › Papers

The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation

2025-03-05 · Findings of the Association for Computational Linguistics 2020 · Jie He, Tao Wang, Deyi Xiong, Qun Liu

Does neural machine translation yield translations that are congenial with common sense? In this paper, we present a test suite to evaluate the commonsense reasoning capability of neural machine translation. The test suite consists of three test sets, covering lexical and contextless/contextual syntactic ambiguity that requires commonsense knowledge to resolve. We manually create 1,200 triples, each of which contain a source sentence and two contrastive translations, involving 7 different common sense types. Language models pretrained on large-scale corpora, such as BERT, GPT-2, achieve a commonsense reasoning accuracy of lower than 72% on target translations of this test suite. We conduct extensive experiments on the test suite to evaluate commonsense reasoning in neural machine translation and investigate factors that have impact on this capability. Our experiments and analyses demonstrate that neural machine translation performs poorly on commonsense reasoning of the three ambiguity types in terms of both reasoning accuracy (60.1%) and reasoning consistency (31%). The built commonsense test suite is available at https://github.com/tjunlp-lab/CommonMT.

📄 PDF Abstract BibTeX arXiv:2503.03308

Code (1)

tjunlp-lab/commonmt 공식 구현

Tasks

Common Sense ReasoningMachine TranslationSentenceTranslation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
WordPiece 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution

2021-11-01 · EMNLP 2021 11 · Denis Emelin, Rico Sennrich

Winograd schemas are a well-established tool for evaluating coreference resolution (CoR) and commonsense reasoning (CSR) capabilities of computational models. So far, schemas remained largely confined to English, limitin…

Common Sense Reasoningcoreference-resolutionCoreference ResolutionMachine Translation+3

Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis

2025-02-17 · Andong Chen, Yuchen Song, Wenxin Zhu, Kehai Chen 외

The o1-Like LLMs are transforming AI by simulating human cognitive processes, but their performance in multilingual machine translation (MMT) remains underexplored. This study examines: (1) how o1-Like LLMs perform in MM…

Machine TranslationTranslation

LOGICAL-COMMONSENSEQA: A Benchmark for Logical Commonsense Reasoning

2026-01-23 · Obed Junias, Maria Leonor Pacheco arxiv

Commonsense reasoning often involves evaluating multiple plausible interpretations rather than selecting a single atomic answer, yet most benchmarks rely on single-label evaluation, obscuring whether statements are joint…

Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding

2021-09-10 · Findings (EMNLP) 2021 11 · Shane Storks, Qiaozi Gao, Yichi Zhang, Joyce Chai

Large-scale, pre-trained language models (LMs) have achieved human-level performance on a breadth of language understanding tasks. However, evaluations only based on end task performance shed little light on machines' tr…

valid

COSMO: Conditional SEQ2SEQ-based Mixture Model for Zero-Shot Commonsense Question Answering

2020-11-02 · COLING 2020 8 · Farhad Moghimifar, Lizhen Qu, Yue Zhuo, Mahsa Baktashmotlagh 외

Commonsense reasoning refers to the ability of evaluating a social situation and acting accordingly. Identification of the implicit causes and effects of a social context is the driving capability which can enable machin…

Question Answering