--- title: "Michael Collins — papers, page 2 — Elamur Research" description: "Michael Collins: 28 papers on Elamur Research (1995–2024), h-index 48 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/michael-collins/page/2/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/michael-collins/page/2/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Michael Collins](https://md.research.elamur.ai/free/en/authors/michael-collins/) / page 2 # Michael Collins · page 2 28 papers in our library · 1995–2024 · page 2 of 2 [The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/michael-collins/) ## Papers The most cited first (OpenAlex and our library). [← prev](https://md.research.elamur.ai/free/en/authors/michael-collins/) [1](https://md.research.elamur.ai/free/en/authors/michael-collins/) **2** 26. **[Coreference Resolution through a seq2seq Transition-Based System](https://md.research.elamur.ai/free/en/papers/bohnet-2023-coreference-resolution-through-seq2seq-transition/)** *(2023 · 77 citations)* The paper reframes coreference resolution, which is usually handled by encoder-only models (e.g., SpanBERT) with span search and separate mention-detection stages, as a pure text-to-text task. 27. **[Unsupervised Part-Of-Speech Tagging with Anchor Hidden Markov Models](https://md.research.elamur.ai/free/en/papers/stratos-2016-unsupervised-part-speech-tagging-anchor/)** *(2016 · 66 citations)* Inducing part-of-speech tags from raw text without any labels is a long-standing unsupervised NLP problem. 28. **[A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains](https://md.research.elamur.ai/free/en/papers/jacovi-2024-chain-thought-is-as-strong/)** *(2024 · 54 citations)* Language models often reach answers through Chain-of-Thought (CoT) reasoning, but a correct final answer can hide flawed intermediate steps. [← prev](https://md.research.elamur.ai/free/en/authors/michael-collins/) [1](https://md.research.elamur.ai/free/en/authors/michael-collins/) **2**