jurafsky&martin_3rdEd_17 (1).pdf

Lets look at the timeml annotation scheme in which

Info icon This preview shows pages 365–367. Sign up to view the full content.

Let’s look at the TimeML annotation scheme, in which temporal expressions are annotated with an XML tag, TIMEX3, and various attributes to that tag ( Pustejovsky et al. 2005 , Ferro et al. 2005 ). The following example illustrates the basic use of this scheme (we defer discussion of the attributes until Section 21.3.2 ). A fare increase initiated < TIMEX3 > last week < /TIMEX3 > by UAL Corp’s United Airlines was matched by competitors over < TIMEX3 > the
Image of page 365

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

366 C HAPTER 21 I NFORMATION E XTRACTION weekend < /TIMEX3 > , marking the second successful fare increase in < TIMEX3 > two weeks < /TIMEX3 > . The temporal expression recognition task consists of finding the start and end of all of the text spans that correspond to such temporal expressions. Rule-based ap- proaches to temporal expression recognition use cascades of automata to recognize patterns at increasing levels of complexity. Tokens are first part-of-speech tagged, and then larger and larger chunks are recognized from the results from previous stages, based on patterns containing trigger words (e.g., February ) or classes (e.g., MONTH ). Figure 21.19 gives a small representative fragment from a rule-based sys- tem written in Perl. # yesterday/today/tomorrow $string =˜ s/(($OT+(early|earlier|later?)$CT+\s+)?(($OT+the$CT+\s+)?$OT+day$CT+\s+ $OT+(before|after)$CT+\s+)?$OT+$TERelDayExpr$CT+(\s+$OT+(morning|afternoon| evening|night)$CT+)?)/<TIMEX2 TYPE=\"DATE\">$1<\/TIMEX2>/gio; $string =˜ s/($OT+\w+$CT+\s+) <TIMEX2 TYPE=\"DATE\"[ˆ>]*>($OT+(Today|Tonight)$CT+)<\/TIMEX2>/$1$2/gso; # this/that (morning/afternoon/evening/night) $string =˜ s/(($OT+(early|earlier|later?)$CT+\s+)?$OT+(this|that|every|the$CT+\s+ $OT+(next|previous|following))$CT+\s*$OT+(morning|afternoon|evening|night) $CT+(\s+$OT+thereafter$CT+)?)/<TIMEX2 TYPE=\"DATE\">$1<\/TIMEX2>/gosi; Figure 21.19 Fragment of Perl code from MITRE’s TempEx temporal tagging system. Sequence-labeling approaches follow the same IOB scheme used for named- entity tags, marking words that are either inside, outside or at the beginning of a TIMEX3-delimited temporal expression with the B, I, and O tags as follows: A O fare O increase O initiated O last B week I by O UAL O Corp’s... O Features are extracted from the token and its context, and a statistical sequence labeler is trained (any sequence model can be used). Figure 21.20 lists standard features used in temporal tagging. Feature Explanation Token The target token to be labeled Tokens in window Bag of tokens in the window around a target Shape Character shape features POS Parts of speech of target and window words Chunk tags Base-phrase chunk tag for target and words in a window Lexical triggers Presence in a list of temporal terms Figure 21.20 Typical features used to train IOB -style temporal expression taggers. Temporal expression recognizers are evaluated with the usual recall, precision, and F -measures. A major difficulty for all of these very lexicalized approaches is avoiding expressions that trigger false positives: (21.15) 1984 tells the story of Winston Smith...
Image of page 366
Image of page 367
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern