Natural Language Processing (NLP) driven categorisation and detection of discourse in historical US patents

Patents have traditionally been used in the history of technology as an indication of the thinking process of the inventors, of the challenges or “reverse salients” they faced, or of the social groups influencing the construction of technology. More recently, historians of science and technology also read them to interpret the way people described technology and how the specific inscriptions of inventions mattered for the justification and operation of the patent system. The digitization of historical patents opens up unique opportunities to assess the feasibility of unsupervised machine learning and natural language methods for such explorations. In this project, we analyze over a million US historical patents from 1830-1930 using a variety of text-based methods, with two major aims: 1) categorizing patents into coherent technical categories, 2) identifying discourses of safety, reflexivity, and environmental concern in technological innovation. We use both frequency-based and context-based methods, and find that a bag of words-based methods such as TDF-IDF and topic modeling do not perform well on semantic categorization due to the linguistic peculiarities of patent specifications. This suggests that a successful approach to categorizing patents would require contextual semantic representations such as Transformers-based methods (e.g. BERT), or static embedding based methods (e.g Word2Vec, Doc2Vec) which have relatively low computational costs but less expressive in some scenarios. We run early experiments using these methods and find that word embedding models are effective in learning semantics from the descriptions of the patents. In this poster, we will describe our early results, as well as exploratory data analysis on this massive historical patents dataset.

Selection bias in innovation studies: A simple test

Gaétan Jean A de Rassenfosse

The study of the innovative output of organizations often relies on a count of patents filed at one single office of reference such as the European Patent Office (EPO). Yet, not all organizations file their patents at the EPO, raising the specter of a selection bias. Using novel datasets of the whole population of patents by Belgian firms and German universities, we show that the single-office count results in a selection bias that affects econometric estimates of invention production functions. We propose an easy-to-implement methodology to evaluate whether estimates that rely on the single-office count are affected by a selection bias. Â© 2013 Elsevier Inc.

2014

The worldwide count of priority patents: A new indicator of inventive activity

Gaétan Jean A de Rassenfosse

This paper describes a new patent-based indicator of inventive activity. The indicator is based on counting all the priority patent applications filed by a country's inventors, regardless of the patent office in which the application is filed, and can therefore be considered as a complete 'matrix' of all patent counts. The method has the advantage of covering more inventions than the selective Patent Cooperation Treaty (PCT) or triadic families counts, while at the same time limiting the home-country bias of single-country-based indicators (inventors from a particular country tend to file in their own country). The indicator is particularly useful to identify emerging technologies and to assess the innovation performance of developing economies. Â© 2012 Elsevier B.V.

2013

Word Sense Consistency in Statistical and Neural Machine Translation

Xiao Pu

Different senses of source words must often be rendered by different words in the target language when performing machine translation (MT). Selecting the correct translation of polysemous words can be done based on the contexts of use. However, state-of-the-art MT algorithms generally work on a sentence-by-sentence basis that ignores information across sentences. In this thesis, we address this problem by studying novel contextual approaches to reduce source word ambiguity in order to improve translation quality. The thesis consists of two parts: the first part is devoted to methods for correcting ambiguous word translations by enforcing consistency across sentences, and the second part investigates sense-aware MT systems that address the ambiguity problem for each word. In the first part, we propose to reduce word ambiguity by using lexical consistency, starting from the one-sense-per-discourse hypothesis. If a polysemous word appears multiple times in a discourse, it is likely that occurrences will share the same sense. We first improve the translation of polysemous nouns (Y) in the case when a previous occurrence of a noun as the head of a compound noun phrase (XY) is available in a text. Experiments on two language pairs show that the translations of the targeted polysemous nouns are significantly improved. As compound pairs X Y /Y appear quite infrequently in texts, we extend our work by analysing the repetition of nouns which are not compounds. We propose a method to decide whether two occurrences of the same noun in a source text should be translated consistently. We design a classifier to predict translation consistency based on syntactic and semantic features. We integrate the classifiersâ output into MT. We experiment on two language pairs and show that our method closes up to 50% of the gap in BLEU scores between the baseline and an oracle classifier. In the second part of the thesis, we design sense-aware MT systems that (automatically) select the correct translations of ambiguous words by performing word sense disambiguation (WSD). We demonstrate that WSD can improve MT by widening the source context considered when modeling the senses of potentially ambiguous words. We first design three adaptive clustering algorithms, respectively based on k-means, Chinese restaurant process and random walk. For phrase-based statistical MT, we integrate the sense knowledge as an additional feature through a factored model and show that the combination improves the translation from English to five other languages. As the sense integration appears promising for SMT, we also transfer this approach to the newer neural MT models, which are now state of the art. However, unlike SMT, for which it is easier to use linguistic features, NMT uses vectors for word generation and traditional feature incorporation does not work here. We design a sense-aware NMT model that jointly learns the sense knowledge using an attention-based sense selection mechanism and concatenates the learned sense vectors with word vectors during encoding . Such a concatenation outperforms several baselines. The improvements are significant over both overall and analysed ambiguous words over the same language pairs we experiment with SMT. Overall, the thesis proves that lexical consistency and WSD are practical and workable solutions that lead to global improvements in translation in ranges of 0.2 to 1.5 BLEU score.

EPFL2018

Word Sense Consistency in Statistical and Neural Machine Translation

Xiao Pu

EPFL2018