We present a new parser for parsing down to Penn tree-bank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less, and 89.5% for sentences of length 100 and less when trained and tested on the previously established [5,9,10,15,17] "stan- dard" sections of the Wall Street Journal tree- bank. This represents a 13% decrease in error rate over the best single-parser results on this corpus [9]. The major technical innova- tion is the use of a "maximum-entropy-inspired" model for conditioning and smoothing that let us successfully to test and combine many different conditioning events. We also present some partial results showing the effects of different conditioning information, including a surprising 2% improvement due to guessing the lexical head's pre-terminal before guessing the lexical head.

This paper presents a statistical model which trains from a corpus annotated with Part-OfSpeech tags and assigns them to previously unseen text with state-of-the-art accuracy(96.6%). The model can be classified as a Maximum Entropy model and simultaneously uses many contextual "features" to predict the POS tag. Furthermore, this paper demonstrates the use of specialized features to model difficult tagging decisions, discusses the corpus consistency problems discovered during the implementation of these features, and proposes a training strategy that mitigates these problems.

Eric Brill introduced transformation-based learning and showed that it can do part-ofspeech tagging with fairly high accuracy. The same method can be applied at a higher level of textual interpretation for locating chunks in the tagged text, including non-recursive "baseNP" chunks. For this purpose, it is convenient to view chunking as a tagging problem by encoding the chunk structure in new tags attached to each word. In automatic tests using Treebank-derived data, this technique achieved recall and precision rates of roughly 92% for baseNP chunks and 88% for somewhat more complex chunks that partition the sentence. Some interesting adaptations to the transformation-based learning approach are also suggested by this application.

This paper presents a simple unsupervised learning algorithm for classifying reviews as recommended (thumbs up) or not recommended (thumbs down). The classification of a review is predicted by the average semantic orientation of the phrases in the review that contain adjectives or adverbs. A phrase has a positive semantic orientation when it has good associations (e.g., "subtle nuances") and a negative semantic orientation when it has bad associations (e.g., "very cavalier"). In this paper, the semantic orientation of a phrase is calculated as the mutual information between the given phrase and the word "excellent" minus the mutual information between the given phrase and the word "poor". A review is classified as recommended if the average semantic orientation of its phrases is positive. The algorithm achieves an average accuracy of 74% when evaluated on 410 reviews from Epinions, sampled from four different domains (reviews of automobiles, banks, movies, and travel destinations). The accuracy ranges from 84% for automobile reviews to 66% for movie reviews.

To solve the mystery of the life phenomenon, we must clarify when genes are expressed and how their products interact with each other. But since the amount of continuously updated knowledge on these interactions is massive and is only available in the form of published articles, an intelligent information extraction (IE) system is needed. To extract these information directly from articles, the system must rstly identify the material names. However, medical and biological documents often include proper nouns newly made by the authors, and conventional methods based on domain speci c dictionaries cannot detect such unknown words or coinages. In this study, we propose a new method of extracting material names, PROPER, using surface clue on character strings. It extracts material names in the sentence with 94.70 % precision and 98.84 % recall, regardless of whether it is already known or newly de ned. 1

The best aspect of a research environment, in my opinion, is the abundance of bright people with whom you argue, discuss, and nurture your ideas. I thank all of the people at Penn and elsewhere who have given me the feedback that has helped me to separate the good ideas from the bad ideas. I hope that Ihave kept the good ideas in this thesis, and left the bad ideas out! Iwould like toacknowledge the following people for their contribution to my education: I thank my advisor Mitch Marcus, who gave me the intellectual freedom to pursue what I believed to be the best way to approach natural language processing, and also gave me direction when necessary. I also thank Mitch for many fascinating conversations, both personal and professional, over the last four years at Penn. I thank all of my thesis committee members: John La erty from Carnegie Mellon University, Aravind Joshi, Lyle Ungar, and Mark Liberman, for their extremely valuable suggestions and comments about my thesis research. I thank Mike Collins, Jason Eisner, and Dan Melamed, with whom I've had many stimulating and impromptu discussions in the LINC lab. Iowe them much gratitude for their valuable feedback onnumerous rough drafts of papers and thesis chapters.

We present a trainable model for identifying sentence boundaries in raw text. Given a corpus annotated with sentence boundaries, our model learns to classify each occurrence of., ?, and ! as either a valid or invalid sentence boundary. The training procedure requires no hand-crafted rules, lexica, part-of-speech tags, or domain-specific information. The model can therefore be trained easily on any genre of English, and should be trainable on any other Romanalphabet language. Performance is comparable to or better than the performance of similar systems, but we emphasize the simplicity of retraining for new domains.

The success of the Semantic Web depends on the availability of ontologies as well as on the proliferation of web pages annotated with metadata conforming to these ontologies. Thus, a crucial question is where to acquire these metadata. In this paper we propose PANKOW (Pattern-based Annotation through Knowledge on the Web), a method which employs an unsupervised, pattern-based approach to categorize instances with regard to an ontology. The approach is evaluated against the manual annotations of two human subjects. The approach is implemented in OntoMat, an annotation tool for the Semantic Web and shows very promising results.

Words unknown to the lexicon present a substantial problem to NLP modules that rely on mor-phosyntactic information, such as part-of-speech taggers or syntactic parsers. In this paper we present a technique for fully automatic acquisition of rules that guess possible part-of-speech tags for unknown words using their starting and ending segments. The learning is performed from a general-purpose lexicon and word frequencies collected from a raw corpus. Three complimentary sets of word-guessing rules are statistically induced: prefix morphological rules, suffix morpho-logical rules and ending-guessing rules. Using the proposed technique, unknown-word-guessing rule sets were induced and integrated into a stochastic tagger and a rule-based tagger, which were then applied to texts with unknown words. 1.

m we can carve o# next. `Partial parsing' is a cover term for a range of di#erent techniques for recovering some but not all of the information contained in a traditional syntactic analysis. Partial parsing techniques, like tagging techniques, aim for reliability and robustness in the face of the vagaries of natural text, by sacrificing completeness of analysis and accepting a low but non-zero error rate. 1 Tagging The earliest taggers [35, 51] had large sets of hand-constructed rules for assigning tags on the basis of words' character patterns and on the basis of the tags assigned to preceding or following words, but they had only small lexica, primarily for exceptions to the rules. TAGGIT [35] was used to generate an initial tagging of the Brown corpus, which was then hand-edited. (Thus it provided the data that has since been used to train other taggers [20].) The tagger described by Garside [56, 34], CLAWS, was a probabilistic version of TAGGIT, and the DeRose tagger improved on