[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/authors/michael-collins/) [home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/) / Michael Collins # Michael Collins 5 paper cards in Mova's library · 1995–2004 Michael Collins wrote 5 of the papers Mova reads, in 1995–2004, most of them on [Part-of-speech tagging](https://md.mova.elamur.ai/free/en/docs/papers/topics/part-of-speech-tagging/); often with Brian Roark, James Brooks, Terry Koo. [OpenAlex](https://openalex.org/A5079061237) · [ORCID](https://orcid.org/0000-0003-0997-1527) · [**h-index 60**](https://openalex.org/authors/A5079061237) · [22998 citations](https://openalex.org/authors/A5079061237) · [244 works](https://openalex.org/works?filter=author.id:A5079061237) — openalex, 2026-10-18 The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Michael+Collins) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Michael+Collins) · [dblp](https://dblp.org/search?q=Michael+Collins) · [ACL Anthology](https://aclanthology.org/search/?q=Michael+Collins) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Michael+Collins) Topics: [Part-of-speech tagging](https://md.mova.elamur.ai/free/en/docs/papers/topics/part-of-speech-tagging/) 1 ## Ideas Mova took (2) From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave. - **kept** — en/src/parse.rs: add a distance feature for each candidate arc (direction, binned distance, and a count of verbs or punctuation between the two words); measure cv LAS on the train folds, then EWT test once per release. *([Head-Driven Statistical Models for Natural Language Parsing](https://md.mova.elamur.ai/free/en/docs/papers/cl-2003-collins-head-driven-statistical-models-natural/) · verbs/punctuation between the pair, on top of conj+subcat: 79.80 -> 79.90 (+0.10, noise level), gold tags 84.41 -> 84.77 (3 shuffles), construction set 62.7…)* - **kept** — en/src/parse.rs: add a subcategorization feature for a verb head, namely which of its obligatory dependents (nsubj, obj, iobj, ccomp, xcomp) are already attached; measure cv LAS and the LAS of verb-headed arcs with en ud-eval. *([Head-Driven Statistical Models for Natural Language Parsing](https://md.mova.elamur.ai/free/en/docs/papers/cl-2003-collins-head-driven-statistical-models-natural/) · subcat bit set of attached core dependents, on top of conj: 79.37 -> 79.80 (+0.43, 3 shuffles), gold tags 84.55; commit 1c729b451)* ## Papers 1. **[Incremental Parsing with the Perceptron Algorithm](https://md.mova.elamur.ai/free/en/docs/papers/collins-2004-incremental-parsing-perceptron-algorithm/)** *(2004)* `measured` The paper asks whether an unnormalised discriminative model can work well together with heuristic search in parsing. 2. **[Head-Driven Statistical Models for Natural Language Parsing](https://md.mova.elamur.ai/free/en/docs/papers/cl-2003-collins-head-driven-statistical-models-natural/)** *(2003)* `2 ideas kept` Collins gives three generative models for lexicalized parsing of the Penn Treebank. A tree is generated top-down from its head: at each step the model chooses the head's modifiers on each side, with distance, subcategorization frames, and for Model 3 traces for wh-movement. Model 1 reaches 87.7% labelled precision… 3. **[Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms](https://md.mova.elamur.ai/free/en/docs/papers/collins-2002-discriminative-training-methods-hidden-markov/)** *(2002)* `measured` The paper proposes training sequence-labelling models, such as part-of-speech taggers and base-NP chunkers, with a perceptron instead of maximum-entropy models or CRFs. 4. **[Discriminative Reranking for Natural Language Parsing](https://md.mova.elamur.ai/free/en/docs/papers/collins-2000-discriminative-reranking-natural-language-parsing/)** *(2000)* `measured` The work splits parsing into two stages. A base probabilistic parser proposes a short list of candidate trees for each sentence together with their probabilities, and a second, discriminatively trained model reorders the list. Because the second model only scores complete candidates, it can use arbitrary, overlapping… 5. **[Prepositional Phrase Attachment through a Backed-off Model](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-1995-collins-prepositional-phrase-attachment-through-backed/)** *(1995)* The paper treats the choice between noun and verb attachment of a prepositional phrase as a language-modeling problem. ## Co-authors (3) - Brian Roark - James Brooks - Terry Koo - [← previous Meni Adler](https://md.mova.elamur.ai/free/en/docs/papers/authors/meni-adler/) - [next → Michael Elhadad](https://md.mova.elamur.ai/free/en/docs/papers/authors/michael-elhadad/) - [↑ back to Authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/)