--- title: "Peter F. Brown — author profile and papers" description: "Peter F. Brown: 3 papers on Elamur Research (1991–1992), h-index 21 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/peter-f-brown/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/peter-f-brown/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Peter F. Brown # Peter F. Brown Peter F. Brown works on statistical methods for natural language. The three papers here, from 1991 and 1992, centre on French–English machine translation and on probabilistic models of written text. The recurring questions are practical ones: how to match translated material line by line, how to choose the right meaning of an ambiguous word, and how well a model can predict English. The tools are drawn from information theory and probability, including hidden Markov models, dynamic programming, mutual information and trigram language models. Most of the training material comes from the Canadian Hansard parliamentary proceedings. The most cited work, [Aligning Sentences in Parallel Corpora](https://md.research.elamur.ai/free/en/papers/brown-1991-aligning-sentences-parallel-corpora/) (1991), pairs English and French Hansard sentences with their translations. It first matches structural markers such as speaker names and timestamps, which splits the corpus into short sections. It then aligns sentences inside each section with a hidden Markov model that looks only at sentence length and paragraph breaks. [Word-Sense Disambiguation Using Statistical Methods](https://md.research.elamur.ai/free/en/papers/brown-1991-word-sense-disambiguation-statistical-methods/) (1991) adds a sense-tagging step before translation. In that paper a sense distinction counts only if it leads to a different rendering in the target language. A flip-flop procedure picks the most informative context feature by repeatedly raising mutual information. The newest paper, [An Estimate of an Upper Bound for the Entropy of English](https://md.research.elamur.ai/free/en/papers/brown-1992-estimate-upper-bound-entropy-english/) (1992), turns from translation to measurement. Earlier estimates in the tradition of Shannon relied on human subjects guessing letters. Instead, the paper uses the cross-entropy of a word trigram model, trained on 583 million words, to bound the per-character entropy of printed English, and tests it on the Brown Corpus. Brown's bylines point to IBM Research's Thomas J. Watson Research Center in Yorktown Heights. Frequent co-authors include [Robert L. Mercer](https://md.research.elamur.ai/free/en/authors/robert-l-mercer/), [Jennifer C. Lai](https://md.research.elamur.ai/free/en/authors/jennifer-c-lai/), [Stephen A. Della Pietra](https://md.research.elamur.ai/free/en/authors/stephen-a-della-pietra/) and [Vincent J. Della Pietra](https://md.research.elamur.ai/free/en/authors/vincent-j-della-pietra/). Among the topics of the papers here is [word sense disambiguation](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/). 3 papers on this site · 1991–1992 Peter F. Brown has 3 papers on this site, in 1991–1992, most of them on [Word sense disambiguation](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/); often with [Robert L. Mercer](https://md.research.elamur.ai/free/en/authors/robert-l-mercer/), [Jennifer C. Lai](https://md.research.elamur.ai/free/en/authors/jennifer-c-lai/), [Stephen A. Della Pietra](https://md.research.elamur.ai/free/en/authors/stephen-a-della-pietra/). [OpenAlex](https://openalex.org/A5103519956) · [**h-index 21**](https://openalex.org/authors/A5103519956) · [36 works](https://openalex.org/works?filter=author.id:A5103519956) · [11 055 citations](https://openalex.org/works?filter=author.id:A5103519956&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [3 works on this site](https://md.research.elamur.ai/free/en/authors/peter-f-brown/#papers) · [2 204 citations in our library](https://md.research.elamur.ai/free/en/authors/peter-f-brown/cited-by/) · 3 more works in our library 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=Peter+F.+Brown) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Peter+F.+Brown) · [dblp](https://dblp.org/search?q=Peter+F.+Brown) · [ACL Anthology](https://aclanthology.org/search/?q=Peter+F.+Brown) ## Affiliations - [IBM Research - Thomas J. Watson Research Center](https://md.research.elamur.ai/free/en/labs/ibm-research-thomas-j-watson-research-center/) · Yorktown Heights, United States —1987–2003 on 19 papers - [IBM (United States)](https://md.research.elamur.ai/free/en/companies/ibm/) · Armonk, United States —1993–2003 on 4 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Topics [Word sense disambiguation 1](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/) ## Works by year ### 1990s [**1992** 1 paper](https://md.research.elamur.ai/free/en/papers/brown-1992-estimate-upper-bound-entropy-english/) · [**1991** 2 papers](https://md.research.elamur.ai/free/en/authors/peter-f-brown/year/1991/) ## Papers The most cited first (OpenAlex and our library). 1. **[Aligning Sentences in Parallel Corpora](https://md.research.elamur.ai/free/en/papers/brown-1991-aligning-sentences-parallel-corpora/)** *(1991 · 657 citations)* Brown, Lai and Mercer address sentence alignment: pairing each sentence in a bilingual corpus with its translation, even when one sentence becomes two or text is dropped on one side. 2. **[Word-Sense Disambiguation Using Statistical Methods](https://md.research.elamur.ai/free/en/papers/brown-1991-word-sense-disambiguation-statistical-methods/)** *(1991 · 464 citations)* Statistical MT systems of this period relied on local models: a trigram language model and a word-alignment translation model. 3. **[An Estimate of an Upper Bound for the Entropy of English](https://md.research.elamur.ai/free/en/papers/brown-1992-estimate-upper-bound-entropy-english/)** *(1992 · 411 citations)* The paper looks for a provable upper limit on the per-character entropy of printed English. Earlier estimates, going back to Shannon (1951), had human subjects guess letters in passages of at most a few hundred characters. The IBM authors use a different principle: a model's cross-entropy on real text can never fall… ## Also in our library 3 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 4 co-authors with a page, the most papers together first. - [Robert L. Mercer](https://md.research.elamur.ai/free/en/authors/robert-l-mercer/) ×3 - [Jennifer C. Lai](https://md.research.elamur.ai/free/en/authors/jennifer-c-lai/) ×2 - [Stephen A. Della Pietra](https://md.research.elamur.ai/free/en/authors/stephen-a-della-pietra/) ×2 - [Vincent J. Della Pietra](https://md.research.elamur.ai/free/en/authors/vincent-j-della-pietra/) ×2 ## Cited by Papers of our library cite their works 2 204 times (of the 140 884 papers whose bibliographies we read); [123 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/peter-f-brown/cited-by/).