Mrinmaya Sachan
12 papers in the PaperMetrix corpus
Papers by this author
-
Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang
2022 · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Languages are continuously undergoing changes, and the mechanisms that underlie these changes are still a matter of debate. In this work, we approach language evolution through the lens of causality in order to model not …
-
BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation
2022 · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Yuchen Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Jian Yang, Haoyang Huang, Rico Sennrich, Ryan Cotterell, Mrinmaya Sachan, Ming Zhou. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational …
-
A Bilingual Parallel Corpus with Discourse Annotations
2022 · arXiv (Cornell University)
Machine translation (MT) has almost achieved human parity at sentence-level translation. In response, the MT community has, in part, shifted its focus to document-level translation. However, the development of document-level MT systems is hampered by …
-
Strategize Before Teaching: A Conversational Tutoring System with Pedagogy Self-Distillation
2023 · arXiv (Cornell University)
Conversational tutoring systems (CTSs) aim to help students master educational material with natural language interaction in the form of a dialog. CTSs have become a key pillar in educational data mining research. A key challenge …
-
Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
2023 · arXiv (Cornell University)
Ideally, dialogue systems should generate responses that are faithful to the knowledge contained in relevant documents. However, many models generate hallucinated responses instead that contradict it or contain unverifiable information. To mitigate such undesirable behaviour, …
-
Discourse Centric Evaluation of Machine Translation with a Densely Annotated Parallel Corpus
2023 · arXiv (Cornell University)
Several recent papers claim human parity at sentence-level Machine Translation (MT), especially in high-resource languages. Thus, in response, the MT community has, in part, shifted its focus to document-level translation. Translating documents requires a deeper …
-
When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP
2023 · SSRN Electronic Journal
Multi-task learning (MTL) aims at achieving a better model by leveraging data and knowledge from multiple tasks. However, MTL does not always work – sometimes negative transfer occurs between tasks, especially when aggregating loosely related …
-
Revisiting Automated Topic Model Evaluation with Large Language Models
2023
Topic models help us make sense of large text collections. Automatically evaluating their output and determining the optimal number of topics are both longstanding challenges, with no effective automated solutions to date. This paper proposes …
-
Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation
2024 · arXiv (Cornell University)
High-quality Machine Translation (MT) evaluation relies heavily on human judgments. Comprehensive error classification methods, such as Multidimensional Quality Metrics (MQM), are expensive as they are time-consuming and can only be done by experts, whose availability …
-
Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors
2024 · arXiv (Cornell University)
Large language models (LLMs) present an opportunity to scale high-quality personalized education to all. A promising approach towards this means is to build dialog tutoring models that scaffold students' problem-solving. However, even though existing LLMs …
-
Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning
2025 · arXiv (Cornell University)
Instruction fine-tuning (IFT) can increase the informativeness of large language models (LLMs), but may reduce their truthfulness. This trade-off arises because IFT steers LLMs to generate responses containing long-tail knowledge that was not well covered …
-
DIRAS: Efficient LLM Annotation of Document Relevance for Retrieval Augmented Generation
2025
Retrieval Augmented Generation (RAG) is widely employed to ground responses to queries on domain-specific documents. But do RAG implementations leave out important information when answering queries that need an integrated analysis of information (e.g., Tell …