Daniel Marcu
Biographic Data
| ID | 6536661 |
|---|---|
| NAME | Daniel Marcu |
| GIVEN NAMES | Daniel |
| FAMILY NAME | Marcu |
| SIGNATURE | MARCU D |
| AFFILIATIONS | USC/ISI — Natural Language Group, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA 90292-6601., . |
| VERIFIED | No |
| TOTAL WORKS | 6 |
| TOTAL CITATIONS | 21 |
| WORKS AS AUTHOR | 6 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2000 |
| LATEST PUBLICATION YEAR | 2010 |
| H-INDEX | 3 |
Re-structuring, Re-labeling, and Re-aligning for Syntax-Based Machine Translation
This article shows that the structure of bilingual material from standard parsing and alignment tools is not optimal for training syntax-based statistical machine translation (SMT) systems. We present three modifications to the MT training data to improve the accuracy of a state-of-the-art syntax MT system: re-structuring changes the syntactic structure of training parse trees to enable reuse of substructures; re-labeling alters bracket labels to…
Measuring Word Alignment Quality for Statistical Machine Translation
Automatic word alignment plays a critical role in statistical machine translation. Unfortunately, the relationship between alignment quality and statistical machine translation performance has not been well understood. In the recent literature, the alignment task has frequently been decoupled from the translation task and assumptions have been made about measuring alignment quality for machine translation which, it turns out, are not justified. I…
Improving Machine Translation Performance by Exploiting Non-Parallel Corpora
We present a novel method for discovering parallel sentences in comparable, non-parallel corpora. We train a maximum entropy classifier that, given a pair of sentences, can reliably determine whether or not they are translations of each other. Using this approach, we extract parallel data from large Chinese, Arabic, and English non-parallel newspaper corpora. We evaluate the quality of the extracted data by showing that it improves the performanc…
Induction of Word and Phrase Alignments for Automatic Document Summarization
Current research in automatic single-document summarization is dominated by two effective, yet naïve approaches: summarization by sentence extraction and headline generation via bagof-words models. While successful in some tasks, neither of these models is able to adequately capture the large set of linguistic devices utilized by humans when they produce summaries. One possible explanation for the widespread use of these models is that good techn…
The Rhetorical Parsing of Unrestricted Texts
Coherent texts are not just simple sequences of clauses and sentences, but rather complex artifacts that have highly elaborate rhetorical structure. This paper explores the extent to which well-formed rhetorical structures can be automatically derived by means of surface-form-based algorithms. These algorithms identify discourse usages of cue phrases and break sentences into clauses, hypothesize rhetorical relations that hold among textual units,…
Perlocutions
The Rhetorical Parsing of Unrestricted Texts
Coherent texts are not just simple sequences of clauses and sentences, but rather complex artifacts that have highly elaborate rhetorical structure. This paper explores the extent to which well-formed rhetorical structures can be automatically derived by means of surface-form-based algorithms. These algorithms identify discourse usages of cue phrases and break sentences into clauses, hypothesize rhetorical relations that hold among textual units,…
Perlocutions
Measuring Word Alignment Quality for Statistical Machine Translation
Automatic word alignment plays a critical role in statistical machine translation. Unfortunately, the relationship between alignment quality and statistical machine translation performance has not been well understood. In the recent literature, the alignment task has frequently been decoupled from the translation task and assumptions have been made about measuring alignment quality for machine translation which, it turns out, are not justified. I…
The Rhetorical Parsing of Unrestricted Texts
Coherent texts are not just simple sequences of clauses and sentences, but rather complex artifacts that have highly elaborate rhetorical structure. This paper explores the extent to which well-formed rhetorical structures can be automatically derived by means of surface-form-based algorithms. These algorithms identify discourse usages of cue phrases and break sentences into clauses, hypothesize rhetorical relations that hold among textual units,…
Perlocutions
Improving Machine Translation Performance by Exploiting Non-Parallel Corpora
We present a novel method for discovering parallel sentences in comparable, non-parallel corpora. We train a maximum entropy classifier that, given a pair of sentences, can reliably determine whether or not they are translations of each other. Using this approach, we extract parallel data from large Chinese, Arabic, and English non-parallel newspaper corpora. We evaluate the quality of the extracted data by showing that it improves the performanc…
Induction of Word and Phrase Alignments for Automatic Document Summarization
Current research in automatic single-document summarization is dominated by two effective, yet naïve approaches: summarization by sentence extraction and headline generation via bagof-words models. While successful in some tasks, neither of these models is able to adequately capture the large set of linguistic devices utilized by humans when they produce summaries. One possible explanation for the widespread use of these models is that good techn…
Measuring Word Alignment Quality for Statistical Machine Translation
Automatic word alignment plays a critical role in statistical machine translation. Unfortunately, the relationship between alignment quality and statistical machine translation performance has not been well understood. In the recent literature, the alignment task has frequently been decoupled from the translation task and assumptions have been made about measuring alignment quality for machine translation which, it turns out, are not justified. I…
Re-structuring, Re-labeling, and Re-aligning for Syntax-Based Machine Translation
This article shows that the structure of bilingual material from standard parsing and alignment tools is not optimal for training syntax-based statistical machine translation (SMT) systems. We present three modifications to the MT training data to improve the accuracy of a state-of-the-art syntax MT system: re-structuring changes the syntactic structure of training parse trees to enable reuse of substructures; re-labeling alters bracket labels to…
Computer Science (6 works) · Linguistics (6 works) · Artificial Intelligence (5 works) · Natural language processing (5 works) · Natural Language Processing Techniques (5 works) · Topic Modeling (5 works) · Machine translation (3 works) · Set (abstract data type (3 works) · Translation (biology (3 works) · Word (group theory (3 works)