Part-of-Speech Tagging with Two Sequential Transducers

Original · EN

We present a method of constructing and using a cascade consisting of a left- and a right-sequential finite-state transducer (FST), T1 and T2, for part-of-speech (POS) disambiguation. Compared to an HMM, this FST cascade has the advantage of significantly higher processing speed, but at the cost of slightly lower accuracy. Applications such as Information Retrieval, where the speed can be more important than accuracy, could benefit from this approach. In the process of tagging, we first assign every word a unique ambiguity class cᵢ that can be looked up in a lexicon encoded by a sequential FST. Every cᵢ is denoted by a single symbol, e.g. [ADJₙOUN], although it represents a set of alternative tags that a given word can occur with. The sequence of the cᵢ of all words of one sentence is the input to our FST cascade. It is mapped by T1, from left to right, to a sequence of reduced ambiguity classes rᵢ. Every rᵢ is denoted by a single symbol, although it represents a set of alternative tags. Intuitively, T1 eliminates the less likely tags from cᵢ, thus creating rᵢ. Finally, T2 maps the sequence of rᵢ, from right to left, to a sequence of single POS tags tᵢ. Intuitively, T2 selects the most likely tᵢ from every rᵢ. The probabilities of all tᵢ, rᵢ, and cᵢ are used only at compile time, not at run time. They do not (directly) occur in the FSTs, but are "implicitly contained" in their structure.