To facilitate future research in unsupervised induction of syntactic structure and to standardize best-practices, we propose a tagset that consists of twelve universal part-of-speech categories. In addition to the tagset, we develop a mapping from 25 different treebank tagsets to this universal set. As a result, when combined with the original treebank data, this universal tagset and mapping produce a dataset consisting of common parts-of-speech for 22 different languages. We highlight the use of this resource via three experiments, that (1) compare tagging accuracies across languages, (2) present an unsupervised grammar induction approach that does not use gold standard part-of-speech tags, and (3) use the universal tags to transfer dependency parsers between languages, achieving state-of-the-art results.

People tweet more than 100 Million times daily, yielding a noisy, informal, but sometimes informative corpus of 140-character messages that mirrors the zeitgeist in an unprecedented manner. The performance of standard NLP tools is severely degraded on tweets. This paper addresses this issue by re-building the NLP pipeline beginning with part-of-speech tagging, through chunking, to named-entity recognition. Our novel T-NER system doubles F1 score compared with the Stanford NER system. T-NER leverages the redundancy inherent in tweets to achieve this performance, using LabeledLDA to exploit Freebase dictionaries as a source of distant supervision. LabeledLDA outperforms cotraining, increasing F1 by 25 % over ten common entity types. Our NLP tools are available at:

We evaluate the statistical dependency parser, Malt, on a new dataset of sentences taken from tweets. We use a version of Malt which is trained on gold standard phrase structure Wall Street Journal (WSJ) trees converted to Stanford labelled dependencies. We observe a drastic drop in performance moving from our in-domain WSJ test set to the new Twitter dataset, much of which has to do with the propagation of part-of-speech tagging errors. Retraining Malt on dependency trees produced by a state-of-the-art phrase structure parser, which has itself been self-trained on Twitter material, results in a significant improvement. We analyse this improvement by examining in detail the effect of the retraining on individual dependency types.

Abstract — The web today is increasingly characterized by social and real-time signals, which we believe represent two frontiers in information retrieval. In this paper, we present Earlybird, the core retrieval engine that powers Twitter’s realtime search service. Although Earlybird builds and maintains inverted indexes like nearly all modern retrieval engines, its index structures differ from those built to support traditional web search. We describe these differences and present the rationale behind our design. A key requirement of real-time search is the ability to ingest content rapidly and make it searchable immediately, while concurrently supporting low-latency, highthroughput query evaluation. These demands are met with a single-writer, multiple-reader concurrency model and the targeted use of memory barriers. Earlybird represents a point in the design space of real-time search engines that has worked well for Twitter’s needs. By sharing our experiences, we hope to spur additional interest and innovation in this exciting space. I.

We investigate the problem of parsing the noisy language of social media. We evaluate four Wall-Street-Journal-trained statistical parsers (Berkeley, Brown, Malt and MST) on a new dataset containing 1,000 phrase structure trees for sentences from microblogs (tweets) and discussion forum posts. We compare the four parsers on their ability to produce Stanford dependencies for these Web 2.0 sentences. We find that the parsers have a particular problem with tweets and that a substantial part of this problem is related to POS tagging accuracy. We attempt three retraining experiments involving Malt, Brown and an in-house Berkeley-style parser and obtain a statistically significant improvement for all three parsers. 1

in streaming text data to detect sudden spikes in frequency. But the dynamic and conversational nature of Twitter makes it hard to select known keywords for monitoring. Here we consider a method of automatically finding noun phrases (NPs) as keywords for event monitoring in Twitter. Finding NPs has two aspects, identifying the boundaries for the subsequence of words which represent the NP, and classifying the NP to a specific broad category such as politics, sports, etc. To classify an NP, we define the feature vector for the NP using not just the words but also the author’s behavior and social activities. Our results show that we can classify many NPs by using a sample of training data from a knowledge-base.

Microblog normalisation methods often utilise complex models and struggle to differentiate between correctly-spelled unknown words and lexical variants of known words. In this paper, we propose a method for constructing a dictionary of lexical variants of known words that facilitates lexical normalisation via simple string substitution (e.g. tomorrow for tmrw). We use context information to generate possible variant and normalisation pairs and then rank these by string similarity. Highlyranked pairs are selected to populate the dictionary. We show that a dictionary-based approach achieves state-of-the-art performance

Past work on learning part-of-speech taggers from tag dictionaries and raw data has reported good results, but the assumptions made about those dictionaries are often unrealistic: due to historical precedents, they assume access to information about labels in the raw and test sets. Here, we demonstrate ways to learn hidden Markov model taggers from incomplete tag dictionaries. Taking the MIN-GREEDY algorithm (Ravi et al., 2010) as a starting point, we improve it with several intuitive heuristics. We also define a simple HMM emission initialization that takes advantage of the tag dictionary and raw data to capture both the openness of a given tag and its estimated prevalence in the raw data. Altogether, our augmentations produce improvements to performance over the original MIN-GREEDY algorithm for both English and Italian data. 1

Tweets are the most up-to-date and inclusive stream of information and commentary on current events, but they are also fragmented and noisy, motivating the need for systems that can extract, aggregate and categorize important events. Previous work on extracting structured representations of events has focused largely on newswire text; Twitter’s unique characteristics present new challenges and opportunities for open-domain event extraction. This paper describes TwiCal— the first open-domain event-extraction and categorization system for Twitter. We demonstrate that accurately extracting an open-domain calendar of significant events from Twitter is indeed feasible. In addition, we present a novel approach for discovering important event categories and classifying extracted events based on latent variable models. By leveraging large volumes of unlabeled data, our approach achieves a 14 % increase in maximum F1 over a supervised baseline. A continuously updating demonstration of our system can be viewed at