← Back to all news

Natural language processing

Classical and neural NLP: translation, question answering, tokenization and the evaluation of language understanding.

2,601 stories · RSS feed

arXiv Machine Learning
Sep 1

A Visual Question Answering Model to Automate Nondestructive Evaluation Image Analysis

This article presents a Visual Question Answering (VQA) model tailored for nondestructive evaluation (NDE) image analysis. The system combines a ResNet‑50 image encoder with a GPT‑2 language generator, allowing inspectors to ask targeted questions such as "Is there a crack?" or "Where is the defect located?" and receive precise answers. By facilitating direct question‑and‑answer interactions, the VQA model aims to improve inspection efficiency, reduce errors, and enhance usability in field scenarios.

By Mehrdad Shafiei Dizaji, Hoda Azari
llmsnlp
More like this →
arXiv AI
Sep 1

Responsible Integration of AI in Cancer Genomics: Barriers, Risks, and Pathways to Trustworthy Clinical Translation

arXiv:2608.30912v1 Announce Type: new Abstract: Artificial intelligence (AI) and natural language processing (NLP) are increasingly used to extract, integrate, and interpret biomedical knowledge rele...

By Bahar \.Ilgen, Yiannos Tolias, Denise K\"uhnert, Paraskevi Papadopoulou, Magnus Westerlund, Dominik Heider, Katharina Ladewig, Georges Hattab
nlpmultimodalsafety
More like this →
arXiv Computation and Language
Sep 1

Learning from Many Voices: Literary MT Using Multi-Reference Human and Synthetic Data

The paper explores how to improve literary machine translation by using datasets that contain multiple valid translations of the same source text. It introduces a filtering framework that selects source texts whose references show meaningful variation while staying faithful, based on semantic similarity. Experiments show that fine‑tuning on medium to high similarity data outperforms low similarity data, and that using only this filtered subset can match or exceed performance achieved with the full unfiltered set. Additionally, the study compares synthetic translations generated by large language models with human expert translations, finding that fine‑tuning on human expert data yields better results in both automatic metrics and human evaluations, underscoring the continued importance of expert translations for literary MT.

By Si Wu, John Wieting, David A. Smith
llmsnlpfine-tuning
More like this →
arXiv AI
Sep 1

Game-Agnostic Value Functions through Automatic JSON Feature Extraction

The paper introduces JSON-Bag VF, a game-agnostic method for training value functions using JSON-Bag prototypes derived from tokenized game trajectories. It demonstrates that Random Forest-based feature selection and game-stage-specific feature selection enhance performance, and that these selections are more critical than prototype-tokenization. Experiments on six tabletop games show that JSON-Bag OSLA outperforms baseline one-step-look-ahead agents in most cases.

By Dien Nguyen, Diego Perez-Liebana
agentsnlp
More like this →
arXiv AI
Sep 1

Do Language Models Reason Across Languages?

The paper investigates whether language models can reason across languages by introducing a two‑hop question answering task that requires inference over two multilingual documents. Results show that models are more sensitive to language variation in answer‑span documents than in bridging documents, and that up to 33% of multilingual cases involve correct final answers despite failing to infer bridging information in the first step. The study also reveals an 18% composition failure rate and proposes a three‑stage SUBQ prompting method that improves accuracy from 10.1% to 66.5%.

By Yan Meng, Wafaa Mohammed, Christof Monz
llmsnlp
More like this →
arXiv Computation and Language
Sep 1

ManGo: Manga Active Narrative Grounding Optimization

ManGo is an unsupervised framework for manga visual question answering that actively selects panels, extracts concise clues, and decides when to stop, creating a compact evidence sketch before answering. It introduces Active Narrative Sketching (ANS) and optimizes its behavior using group-relative policy training with two rewards: answer preference from listwise self-ranking and path consistency from stable ordered panel trajectories. Experiments on standard manga understanding benchmarks demonstrate that ManGo achieves state‑of‑the‑art performance across different settings.

By Hao Qiu, Junyan Wang, Zheyuan Liu, Lei Fan, Hong Jia, Lianbo Guo, Zhulin Tao
nlpbenchmarks
More like this →
arXiv Computation and Language
Sep 1

ACTD: Anchor-Based Cross-Tokenizer Distillation with Residual Regularization

The paper introduces ACTD, an Anchor-Based Cross-Tokenizer Distillation method that aligns vocabularies and sequences to transfer reasoning capabilities from large language models to smaller students. It uses a novel anchor loss with residual regularization to reduce alignment noise and extends the approach to multiple teachers. Experiments on five reasoning benchmarks with three teachers show state‑of‑the‑art results, with the multi‑teacher variant outperforming existing baselines.

By Huiyi Zhang, Zijian Li, Xiaocheng Feng, Weitao Ma, Xiaoliang Yang, Yichong Huang, Bing Qin
llmsnlpefficiencybenchmarkssafety
More like this →
arXiv AI
Sep 1

AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP

arXiv:2608.30107v1 Announce Type: cross Abstract: Understanding which countries are represented in NLP datasets is essential for identifying gaps, targeting data collection, measuring progress, and i...

By Joan Nwatu, Tsedeniya Solomon Amare, Longju Bai, Bontu Fufa Balcha, Zayd Bashir, Angana Borah, Zara Burzo, Yubin Choi, Naihao Deng, Samika Gupta, Michel Faloughi, Claude Kwizera, Ziqiao Ma, Cynthia Yacel Fuertes Panizo, Ellie Seehorn, Hui Shen, Jiayi Tang, Zesen Zhao, Boyuan Zheng, Rada Mihalcea
nlp
More like this →