Learning algorithms for semantic parsing have improved drastically over the past decade, as steady improvements on bench-mark datasets have shown. In this pa-per we investigate whether they can gen-eralize to a novel biomedical dataset that differs in important respects from the tra-ditional geography and air travel bench-mark datasets. Empirical results for two state-of-the-art PCCG semantic parsers in-dicates that learning algorithms are sensi-tive to the kinds of semantic and syntac-tic constructions used in a domain. In re-sponse, we develop a novel learning algo-rithm that can produce an effective seman-tic parser for geography, as well as a much better semantic parser for the biomedical dataset. 1

Linguist Code Switching (LCS) is a situation where two or more languages show up in the context of a single conversation. For example, in EnglishChinese code switching, there might be a sentence like “· ‚15© ¨ k ‡meeting (We will have a meeting in 15 minutes)”. Traditional machine translation (MT) systems treat LCS data as noise, or just as regular sentences. However, if LCS data is processed intelligently, it can provide a useful signal for training word alignment and MT models. Moreover, LCS data is from non-news sources which can enhance the diversity of training data for MT. In this paper, we first extract constraints from this code switching data and then incorporate them into a word alignment model training procedure. We also show that by using the code switching data, we can jointly train a word alignment model and a language model using cotraining. Our techniques for incorporating LCS data improve by 2.64 in BLEU score over a baseline MT system trained using only standard sentence-aligned corpora.

Finding the right representations for words is critical for building accurate NLP systems when domain-specific labeled data for the task is scarce. This article investigates novel techniques for extracting features from n-gram models, Hidden Markov Models, and other statistical language models, including a novel Partial Lattice Markov Random Field model. Experiments on part-of-speech tagging and information extraction, among other tasks, indicate that features taken from statistical language models, in combination with more traditional features, outperform traditional representations alone, and that graphical model representations outperform n-gram models, especially on sparse and polysemous words.

Recognizing names and linking them to structured data is a fundamental task in text analysis. Existing approaches typically perform these two steps using a pipeline architecture: they use a Named-Entity Recognition (NER) system to find the boundaries of mentions in text, and an Entity Linking (EL) system to connect the mentions to entries in structured or semi-structured repositories like Wikipedia. However, the two tasks are tightly coupled, and each type of system can benefit significantly from the kind of information provided by the other. We present a joint model for NER and EL, called NEREL, that takes a large set of candidate mentions from typical NER systems and a large set of candidate entity links from EL systems, and ranks the candidate mention-entity pairs together to make joint predictions. In NER and EL experiments across three datasets, NEREL significantly outperforms or comes close to the performance of two state-of-the-art NER systems, and it outperforms 6 competing EL systems. On the benchmark MSNBC dataset, NEREL provides a 60% reduction in error over the next-best NER system and a 68% reduction in error over the next-best EL system.

BACKGROUND: We aim to solve the problem of determining word senses for ambiguous biomedical terms with minimal human effort. METHODS: We build a fully automated system for Word Sense Disambiguation by designing a system that does not require manually-constructed external resources or manually-labeled training examples except for a single ambiguous word. The system uses a novel and efficient graph-based algorithm to cluster words into groups that have the same meaning. Our algorithm follows the principle of finding a maximum margin between clusters, determining a split of the data that maximizes the minimum distance between pairs of data points belonging to two different clusters. RESULTS: On a test set of 21 ambiguous keywords from PubMed abstracts, our system has an average accuracy of 78%, outperforming a state-of-the-art unsupervised system by 2% and a baseline technique by 23%. On a standard data set from the National Library of Medicine, our system outperforms the baseline by 6% and comes within 5% of the accuracy of a supervised system. CONCLUSION: Our system is a novel, state-of-the-art technique for efficiently finding word sense clusters, and does not require training data or human effort for each new word to be disambiguated.

The task of identifying synonymous relations and objects, or synonym resolution, is critical for high-quality information extraction. This paper investigates synonym resolution in the context of unsupervised information extraction, where neither hand-tagged training examples nor domain knowledge is available. The paper presents a scalable, fully-implemented system that runs in O(KN log N) time in the number of extractions, N, and the maximum number of synonyms per word, K. The system, called Resolver , introduces a probabilistic relational model for predicting whether two strings are co-referential based on the similarity of the assertions containing them. On a set of two million assertions extracted from the Web, Resolver resolves objects with 78% precision and 68% recall, and resolves relations with 90% precision and 35% recall. Several variations of resolver's probabilistic model are explored, and experiments demonstrate that under appropriate conditions these variations can improve F1 by 5%. An extension to the basic Resolver system allows it to handle polysemous names with 97% precision and 95% recall on a data set from the TREC corpus.

This paper describes a new method for providing recommendations tailored to a user's preferences using text mining techniques and online technical specifications of products. We first learn a model that can predict the price of a product given automatically-determined features describing technical specifications and users' opinions. We then use this model to rank a list of products based on individual users' preferences about various features. On a data set collected from Amazon reviews and online technical specifications, rankings produced by this model rank the best product for a user in the 87th percentile of products in its category, on average. Our approach outperforms several comparison systems by 21 percentiles or more.

Manually querying search engines in order to accumulate a large bodyof factual information is a tedious, error-prone process of piecemealsearch. Search engines retrieve and rank potentially relevantdocuments for human perusal, but do not extract facts, assessconfidence, or fuse information from multiple documents. This paperintroduces KnowItAll, a system that aims to automate the tedious process ofextracting large collections of facts from the web in an autonomous,domain-independent, and scalable manner.The paper describes preliminary experiments in which an instance of KnowItAll, running for four days on a single machine, was able to automatically extract 54,753 facts. KnowItAll associates a probability with each fact enabling it to trade off precision and recall. The paper analyzes KnowItAll's architecture and reports on lessons learned for the design of large-scale information extraction systems.

As household appliances grow in complexity and sophistication, they become harder and harder to use, particularly because of their tiny display screens and limited keyboards. This paper describes a strategy for building natural language interfaces to appliances that circumvents these problems. Our approach leverages decades of research on planning and natural language interfaces to databases by reducing the appliance problem to the database problem; the reduction provably maintains desirable properties of the database interface. The paper goes on to describe the implementation and evaluation of the EXACT interface to appliances, which is based on this reduction. EXACT maps each English user request to an SQL query, which is transformed to create a PDDL goal, and uses the Blackbox planner [13] to map the planning problem to a sequence of appliance commands that satisfy the original request. Both theoretical arguments and experimental evaluation show that EXACT is highly reliable

As product prices become increasingly available on the World Wide Web, consumers attempt to understand how corporations vary these prices over time. However, corporations change prices based on proprietary algorithms and hidden variables (e.g., the number of unsold seats on a flight). Is it possible to develop data mining techniques that will enable consumers to predict price changes under these conditions?This paper reports on a pilot study in the domain of airline ticket prices where we recorded over 12,000 price observations over a 41 day period. When trained on this data, Hamlet --- our multi-strategy data mining algorithm --- generated a predictive model that saved 341 simulated passengers $198,074 by advising them when to buy and when to postpone ticket purchases. Remarkably, a clairvoyant algorithm with complete knowledge of future prices could save at most $320,572 in our simulation, thus HAMLET's savings were 61.8% of optimal. The algorithm's savings of $198,074 represents an average savings of 23.8% for the 341 passengers for whom savings are possible. Overall, HAMLET saved 4.4% of the ticket price averaged over the entire set of 4,488 simulated passengers. Our pilot study suggests that mining of price data available over the web has the potential to save consumers substantial sums of money per annum.